© 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
    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. 5267
    Prev
    Next
    INDEX
    Explanations

    adjectives and verbs related to storytelling and adaptation in literature and film

    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
    393
    +0.21
    0.7%
    296
    +0.17
    0.6%
    409
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.21
    0.10
    608
    +0.17
    0.10
    385
    +0.14
    0.09
    Negative Logits
    ndra
    -1.15
    ggle
    -1.07
    achine
    -1.01
    etsk
    -0.98
    tu
    -0.97
    lear
    -0.93
    boxing
    -0.91
    resy
    -0.91
    care
    -0.91
    cup
    -0.90
    POSITIVE LOGITS
     scripture
    1.27
     excerpts
    1.25
     copyrighted
    1.20
     manuscript
    1.07
     Seasons
    1.00
     scriptures
    1.00
     Shakespeare
    0.98
     Scriptures
    0.94
     classics
    0.94
     autobiography
    0.93
    Activations Density 2.286%

    No Known Activations