© 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. 3825
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss reasons or causes for certain situations

    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
    447
    +0.21
    1.0%
    679
    +0.15
    0.7%
    393
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    264
    +0.21
    0.06
    642
    +0.15
    0.03
    334
    +0.13
    0.05
    Negative Logits
    thal
    -0.72
    yan
    -0.68
    robe
    -0.67
    alin
    -0.65
    ice
    -0.62
    iPhone
    -0.60
    ices
    -0.59
    Syria
    -0.59
    ilet
    -0.58
    mint
    -0.58
    POSITIVE LOGITS
    */(
    0.84
    ecause
    0.72
    assetsadobe
    0.72
     they
    0.68
    ghai
    0.66
     someone
    0.66
    liga
    0.66
    udo
    0.65
    xual
    0.63
    soever
    0.61
    Activations Density 7.506%

    No Known Activations