© 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. 34842
    Prev
    Next
    INDEX
    Explanations

    proper nouns and locations related to a specific geographical area

    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
    +0.17
    0.7%
    143
    +0.12
    0.5%
    538
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.17
    0.21
    659
    +0.12
    0.22
    314
    +0.12
    -0.05
    Negative Logits
     oneself
    -0.95
     laz
    -0.79
     spor
    -0.77
     pear
    -0.77
    etheless
    -0.74
    anwhile
    -0.74
    hetically
    -0.72
    theless
    -0.70
     sidel
    -0.70
     diplom
    -0.70
    POSITIVE LOGITS
    eni
    0.89
    Hot
    0.84
     Alive
    0.79
    Walk
    0.79
    Wallet
    0.76
    License
    0.74
    Union
    0.74
    ometown
    0.73
    Cent
    0.71
     counterparts
    0.71
    Activations Density 17.271%

    No Known Activations