© 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. 40406
    Prev
    Next
    INDEX
    Explanations

    links or URLs

    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
    219
    +0.10
    0.4%
    727
    +0.09
    0.4%
    594
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    145
    +0.10
    0.06
    767
    +0.09
    0.07
    308
    +0.09
    0.05
    Negative Logits
    busters
    -0.71
    milo
    -0.70
    illas
    -0.66
    urally
    -0.66
    Americans
    -0.62
    matically
    -0.62
    Ö¼
    -0.62
    Grade
    -0.61
     majorities
    -0.61
    coded
    -0.60
    POSITIVE LOGITS
     Lumpur
    0.91
    /?
    0.87
    cknow
    0.84
     âĢº
    0.83
    tml
    0.76
    gypt
    0.75
    fc
    0.75
    anse
    0.74
    dq
    0.73
    /-
    0.73
    Activations Density 4.950%

    No Known Activations