© 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. 4152
    Prev
    Next
    INDEX
    Explanations

    descriptions or narrations of personal experiences or stories

    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
    480
    +0.21
    1.9%
    447
    +0.16
    1.4%
    351
    +0.08
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    351
    +0.21
    0.17
    480
    +0.16
    -0.16
    283
    +0.08
    0.00
    Negative Logits
    ortium
    -0.42
     Cosponsors
    -0.40
     Revision
    -0.36
     Econom
    -0.35
     Historically
    -0.34
     Journalism
    -0.33
     Polit
    -0.33
     Reconstruction
    -0.32
     nutshell
    -0.32
    ylum
    -0.32
    POSITIVE LOGITS
     undet
    0.42
     whatever
    0.39
     afterwards
    0.38
     refill
    0.37
     eternity
    0.37
     erection
    0.37
     snack
    0.36
    omever
    0.36
    atever
    0.35
     whichever
    0.35
    Activations Density 37.810%

    No Known Activations