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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 13937
    Prev
    Next
    INDEX
    Explanations

    topics related to significant issues or conflicts at the core of a 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
    99
    +0.18
    0.6%
    616
    +0.14
    0.5%
    659
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.18
    0.06
    759
    +0.14
    0.05
    616
    +0.14
    0.04
    Negative Logits
     peers
    -0.97
     spores
    -0.92
    orks
    -0.89
     Cooper
    -0.88
     roomm
    -0.87
    atern
    -0.86
    /-
    -0.86
     mates
    -0.85
     elders
    -0.84
    byter
    -0.84
    POSITIVE LOGITS
     è£ıè
    1.20
    waters
    1.10
    ICLE
    1.04
    most
    1.03
    phal
    1.01
    stone
    0.99
    GROUND
    0.96
    verse
    0.96
     wedge
    0.95
    Site
    0.94
    Activations Density 0.820%

    No Known Activations