© 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
    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. 3919
    Prev
    Next
    INDEX
    Explanations

    acronyms, proper nouns, and technical terms in the field of research and policy-making

    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
    218
    +0.07
    0.6%
    146
    +0.06
    0.5%
    209
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.07
    0.07
    406
    +0.06
    0.09
    90
    +0.06
    0.08
    Negative Logits
    acters
    -0.38
    strings
    -0.38
    acity
    -0.37
    hold
    -0.34
    icles
    -0.34
    à
    -0.34
    izen
    -0.33
    acious
    -0.33
     ç¥ŀ
    -0.32
    ogen
    -0.32
    POSITIVE LOGITS
    OT
    0.51
    HY
    0.51
    HS
    0.50
    OP
    0.49
    AR
    0.48
    HA
    0.47
    OPS
    0.47
    OD
    0.47
    ALT
    0.46
    AN
    0.45
    Activations Density 5.714%

    No Known Activations