Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4437
    Prev
    Next
    INDEX
    Explanations

    elements related to web development like HTML tags, CSS properties, and JavaScript functions

    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
    385
    +0.15
    0.6%
    653
    +0.13
    0.5%
    160
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    394
    +0.15
    0.05
    63
    +0.13
    0.07
    572
    +0.12
    0.06
    Negative Logits
    etheless
    -0.91
     fortun
    -0.88
     destro
    -0.86
    owers
    -0.80
    İĭ
    -0.78
     Winchester
    -0.77
    eele
    -0.75
     Watts
    -0.74
     Wonderland
    -0.73
    uries
    -0.72
    POSITIVE LOGITS
    wcsstore
    1.20
    ><
    1.11
    !--
    1.04
    span
    0.97
    font
    0.95
    "><
    0.89
    >
    0.88
    img
    0.88
    TABLE
    0.85
     ><
    0.84
    Activations Density 2.853%

    No Known Activations