Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 538
    Prev
    Next
    INDEX
    Explanations

    information related to current events and social media updates

    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
    267
    +0.12
    0.4%
    373
    +0.12
    0.4%
    326
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.12
    -0.00
    170
    +0.12
    0.02
    407
    +0.10
    0.02
    Negative Logits
    ĪĴ
    -0.78
     lobb
    -0.78
     prevailing
    -0.75
     Elias
    -0.74
     nomine
    -0.74
     lim
    -0.74
     possession
    -0.72
     utilities
    -0.72
     Romanian
    -0.72
     telecommunications
    -0.72
    POSITIVE LOGITS
    cdn
    1.18
    twitter
    0.93
    journal
    0.91
    doi
    0.90
    chrom
    0.86
    books
    0.86
     Appears
    0.86
    cp
    0.85
    dp
    0.84
    fff
    0.84
    Activations Density 0.012%

    No Known Activations