© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 40945
    Prev
    Next
    INDEX
    Explanations

    technical and scientific information related to various fields, such as chemistry, space technology, and computer programming

    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
    +0.34
    1.6%
    578
    +0.10
    0.4%
    374
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    206
    +0.34
    0.11
    301
    +0.10
    0.10
    578
    +0.09
    0.05
    Negative Logits
     Newman
    -0.62
    sw
    -0.58
     lights
    -0.55
    serv
    -0.54
    wake
    -0.54
     Islands
    -0.53
     Koreans
    -0.53
     conqu
    -0.50
     Rudd
    -0.50
     extent
    -0.49
    POSITIVE LOGITS
    ometimes
    0.85
    imentary
    0.82
    omething
    0.80
    hirt
    0.76
    Downloadha
    0.76
    anamo
    0.76
    hift
    0.71
    olate
    0.69
    enance
    0.69
    ensibly
    0.68
    Activations Density 9.752%

    No Known Activations