© 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. 14052
    Prev
    Next
    INDEX
    Explanations

    references to fundraising and support through a crowdfunding platform like Kickstarter

    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
    385
    +0.20
    0.7%
    598
    +0.14
    0.5%
    313
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    598
    +0.20
    0.04
    313
    +0.14
    0.05
    433
    +0.14
    0.05
    Negative Logits
    dayName
    -0.92
    ĪĴ
    -0.89
     Hung
    -0.87
    uku
    -0.87
    obin
    -0.86
     Samar
    -0.86
     measles
    -0.85
    obar
    -0.84
    ROR
    -0.81
    ls
    -0.81
    POSITIVE LOGITS
    starter
    1.13
     backer
    1.13
     backers
    1.12
     Kickstarter
    1.02
     Stretch
    0.96
    Kick
    0.95
    Stretch
    0.92
     Patreon
    0.91
    backer
    0.88
     pledge
    0.86
    Activations Density 1.378%

    No Known Activations