© 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
    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. 45986
    Prev
    Next
    INDEX
    Explanations

    information related to lamps, induction, fluorescence, and electrodes

    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
    +0.26
    1.2%
    375
    +0.10
    0.4%
    528
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.26
    0.12
    375
    +0.10
    0.04
    743
    +0.10
    0.04
    Negative Logits
    tty
    -0.72
    Pixel
    -0.65
    ÙĴ
    -0.64
    Bloom
    -0.63
     Nielsen
    -0.63
    pit
    -0.62
     nails
    -0.61
     dads
    -0.61
    natureconservancy
    -0.59
    sels
    -0.59
    POSITIVE LOGITS
    govtrack
    0.63
     Rebirth
    0.60
     Extras
    0.60
    eve
    0.59
    usting
    0.58
    hibited
    0.58
     coli
    0.57
     occurs
    0.57
    mma
    0.57
     occurred
    0.56
    Activations Density 20.609%

    No Known Activations