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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 13906
    Prev
    Next
    INDEX
    Explanations

    references related to unicorns and places within the context of a specific narrative or story

    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
    688
    +0.13
    0.6%
    551
    +0.13
    0.6%
    284
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.10
    288
    +0.13
    0.12
    99
    +0.11
    0.07
    Negative Logits
     Quin
    -0.76
    ugal
    -0.74
    ilty
    -0.72
    uge
    -0.71
    iken
    -0.70
    eal
    -0.68
    enance
    -0.68
     testament
    -0.67
    ernandez
    -0.66
    ruct
    -0.65
    POSITIVE LOGITS
     Sparkle
    0.97
    tailed
    0.95
    tail
    0.92
    toe
    0.84
    hyde
    0.82
    tails
    0.80
    erton
    0.79
    plex
    0.78
    urrent
    0.77
    cess
    0.77
    Activations Density 1.320%

    No Known Activations