© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12632
    Prev
    Next
    INDEX
    Explanations

    phrases related to narrative storytelling, potential dangers, and personal reflections

    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
    699
    +0.02
    0.5%
    271
    +0.01
    0.5%
    678
    +0.01
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    655
    +0.02
    0.02
    214
    +0.01
    0.02
    512
    +0.01
    0.02
    Negative Logits
    orters
    -0.10
    ciplinary
    -0.10
    aqu
    -0.10
    ositories
    -0.10
    ffee
    -0.10
    acco
    -0.09
    unctions
    -0.09
     Aad
    -0.09
    Å¡
    -0.09
    fed
    -0.09
    POSITIVE LOGITS
    WARE
    0.11
    ties
    0.10
    edIn
    0.10
    orage
    0.10
     timing
    0.10
    icular
    0.10
    MENTS
    0.10
    DCS
    0.09
    rals
    0.09
    OGR
    0.09
    Activations Density 0.081%

    No Known Activations