© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 3670
    Prev
    Next
    INDEX
    Explanations

    quotations or reported statements and references to specific individuals and their actions

    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
    640
    +0.28
    1.1%
    220
    +0.14
    0.5%
    513
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.28
    0.26
    160
    +0.14
    0.15
    64
    +0.13
    -0.08
    Negative Logits
    anski
    -1.05
     princ
    -1.03
     tremend
    -0.92
    uca
    -0.89
     granite
    -0.88
     bang
    -0.86
    zona
    -0.83
     disguise
    -0.81
     dissu
    -0.80
     lashes
    -0.80
    POSITIVE LOGITS
    TAG
    1.32
    Copyright
    1.19
    Support
    1.13
    License
    1.13
    NPR
    1.11
    Quotes
    1.11
    YR
    1.08
    TOP
    1.06
    Topics
    1.06
    Thirty
    1.06
    Activations Density 2.011%

    No Known Activations