© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 4638
    Prev
    Next
    INDEX
    Explanations

    terms related to cellular technology, including words like "cellular," "telephone," "communication," and specific technical details such as "neuronal" and "molecular."

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    116
    +0.08
    0.7%
    153
    +0.07
    0.5%
    99
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.08
    0.23
    326
    +0.07
    0.23
    153
    +0.06
    0.09
    Negative Logits
    imaru
    -0.60
    terness
    -0.53
    lins
    -0.51
    wright
    -0.50
    owitz
    -0.50
    lag
    -0.48
    eful
    -0.48
    ful
    -0.47
    riors
    -0.46
    jin
    -0.46
    POSITIVE LOGITS
     autom
    0.49
     melan
    0.47
     cellular
    0.46
     uptake
    0.45
     Cellular
    0.43
     capacity
    0.43
     resp
    0.43
     modem
    0.41
     telephone
    0.40
     Telecommunications
    0.40
    Activations Density 8.662%

    No Known Activations