© 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. 33131
    Prev
    Next
    INDEX
    Explanations

    abbreviations and technical terms used in technical and research texts

    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
    718
    +0.03
    0.6%
    231
    +0.03
    0.5%
    332
    +0.03
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    328
    +0.03
    0.05
    718
    +0.03
    0.11
    606
    +0.03
    0.09
    Negative Logits
    places
    -0.19
    enfranch
    -0.18
    woman
    -0.18
    tops
    -0.18
    cffffcc
    -0.17
    mort
    -0.17
     NCT
    -0.17
    notice
    -0.17
    quote
    -0.17
    ions
    -0.16
    POSITIVE LOGITS
    OLOG
    0.23
    pps
    0.23
    irtual
    0.23
    FFER
    0.23
    OLOGY
    0.22
    adoes
    0.21
    iatrics
    0.21
    BIP
    0.21
    BILITIES
    0.20
    ORED
    0.20
    Activations Density 8.787%

    No Known Activations