Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 209
    Prev
    Next
    INDEX
    Explanations

    text related to social issues, political dialogue, and DIY projects

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    144
    +0.05
    0.5%
    319
    +0.05
    0.5%
    556
    +0.05
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    697
    +0.05
    0.03
    354
    +0.05
    0.02
    556
    +0.05
    0.02
    Negative Logits
    inia
    -0.40
    meaning
    -0.37
    HF
    -0.37
    gran
    -0.36
    APS
    -0.35
    س
    -0.34
    SPONSORED
    -0.33
    nces
    -0.33
    ع
    -0.32
    BIL
    -0.32
    POSITIVE LOGITS
    auts
    0.38
    aut
    0.35
     expect
    0.34
    icans
    0.33
    swer
    0.32
    iverse
    0.32
    't
    0.32
     Osw
    0.32
     nominate
    0.31
    rison
    0.31
    Activations Density 0.051%

    No Known Activations