© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 34793
    Prev
    Next
    INDEX
    Explanations

    code snippets and technical terms commonly found in software development and internet content

    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%
    182
    +0.11
    0.5%
    683
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    293
    +0.15
    0.19
    338
    +0.11
    0.18
    182
    +0.11
    0.17
    Negative Logits
     mathemat
    -0.92
     disadvant
    -0.90
     carbohyd
    -0.88
     mosqu
    -0.76
    wana
    -0.75
    merce
    -0.69
    pheus
    -0.68
     fortun
    -0.68
     Gutenberg
    -0.68
    ĵĺ
    -0.67
    POSITIVE LOGITS
    ï¸ı
    1.16
    女
    0.88
    VERTISEMENT
    0.79
    ship
    0.79
    ï¸
    0.77
    UAL
    0.77
    STON
    0.76
    eric
    0.76
    ution
    0.76
    Balt
    0.74
    Activations Density 11.096%

    No Known Activations