© 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 Local
    5. 6-RES_SCL-AJT
    6. 13723
    Prev
    Next
    INDEX
    Explanations

    links to website URLs

    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
    506
    +0.13
    0.5%
    447
    +0.12
    0.5%
    394
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    709
    +0.13
    0.15
    326
    +0.12
    0.24
    288
    +0.12
    0.23
    Negative Logits
     TAMADRA
    -0.80
     Pants
    -0.80
     Stout
    -0.79
    ï¸
    -0.79
     Conclusion
    -0.77
    BILITIES
    -0.77
    ãĤ©
    -0.77
     Goldberg
    -0.76
     âľĵ
    -0.75
     Eighth
    -0.73
    POSITIVE LOGITS
    pedia
    1.27
    cdn
    1.25
    online
    1.20
    amazon
    1.07
    ecd
    1.07
    research
    1.03
    foundation
    0.97
    library
    0.97
    archives
    0.94
    central
    0.93
    Activations Density 11.457%

    No Known Activations