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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 39885
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions, neurological research, and possible treatments

    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
    149
    +0.12
    0.7%
    213
    +0.09
    0.5%
    4
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.23
    326
    +0.09
    0.20
    99
    +0.09
    0.11
    Negative Logits
     Polo
    -0.53
    plings
    -0.50
    steen
    -0.50
     Vikings
    -0.49
    RED
    -0.48
     Dome
    -0.48
     Loyal
    -0.47
     Crusader
    -0.47
     whichever
    -0.47
    nit
    -0.45
    POSITIVE LOGITS
    ically
    0.90
    istically
    0.88
    yth
    0.77
    ally
    0.76
    ical
    0.73
    y
    0.70
    icably
    0.69
    icter
    0.69
    oped
    0.69
    istics
    0.69
    Activations Density 7.015%

    No Known Activations