© 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. 34744
    Prev
    Next
    INDEX
    Explanations

    names of individuals or entities with '-ness' or '-tion' suffixes

    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
    101
    +0.05
    0.5%
    694
    +0.05
    0.5%
    202
    +0.04
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    709
    +0.05
    0.13
    373
    +0.05
    -0.27
    100
    +0.04
    0.07
    Negative Logits
     Keane
    -0.34
    Kay
    -0.30
     McCoy
    -0.30
    isks
    -0.28
    rodu
    -0.28
    aryl
    -0.27
     orphans
    -0.27
     RAD
    -0.26
    vas
    -0.26
    espie
    -0.26
    POSITIVE LOGITS
    sembly
    0.38
     bloc
    0.37
     congr
    0.35
    ãĥ´ãĤ¡
    0.33
    puter
    0.32
    ariat
    0.31
    ittee
    0.30
    mun
    0.30
    nah
    0.30
    iership
    0.29
    Activations Density 16.222%

    No Known Activations