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. 40120
    Prev
    Next
    INDEX
    Explanations

    technical details and specifications related to electronic devices

    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%
    420
    +0.10
    0.5%
    750
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.21
    0.35
    375
    +0.10
    0.05
    608
    +0.09
    0.21
    Negative Logits
    iol
    -0.65
    Limited
    -0.62
    wind
    -0.59
    ãĤĬ
    -0.59
     (@
    -0.57
    Premium
    -0.57
    WIND
    -0.56
    ãĤ°
    -0.56
    beck
    -0.56
    Ability
    -0.56
    POSITIVE LOGITS
     previous
    0.77
     typical
    0.75
     ours
    0.75
     usual
    0.75
     counterparts
    0.75
     predecessors
    0.72
    gypt
    0.71
     Jas
    0.70
     predecessor
    0.69
    anus
    0.69
    Activations Density 23.457%

    No Known Activations