© 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. 3747
    Prev
    Next
    INDEX
    Explanations

    words related to programming and software development

    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
    +0.15
    0.7%
    420
    +0.15
    0.7%
    99
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.15
    0.31
    138
    +0.15
    0.30
    64
    +0.14
    -0.17
    Negative Logits
    ãĥ¼ãĥĨ
    -0.89
    ctica
    -0.82
    ãĥ´ãĤ¡
    -0.82
    lished
    -0.79
    ãĥ
    -0.79
    ITY
    -0.78
    ity
    -0.78
    Downloadha
    -0.77
    ãĥĨ
    -0.77
    ãĤ¢ãĥ«
    -0.76
    POSITIVE LOGITS
    ldon
    1.04
    oman
    0.96
    ats
    0.93
    aser
    0.92
    asers
    0.91
    asing
    0.89
    lda
    0.89
    velt
    0.88
    erk
    0.88
    asure
    0.80
    Activations Density 7.040%

    No Known Activations