© 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 EvalsExportsinterp-engineNEWAPI 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. 2468
    Prev
    Next
    INDEX
    Explanations

    financial and legal documents

    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
    481
    +0.17
    0.6%
    178
    +0.14
    0.5%
    412
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    409
    +0.17
    0.03
    412
    +0.14
    0.04
    530
    +0.14
    0.03
    Negative Logits
    avorite
    -0.91
     Mahjong
    -0.82
     Doodle
    -0.82
     Degree
    -0.81
    xit
    -0.81
    wav
    -0.81
    unks
    -0.78
     Triangle
    -0.75
    «ĺ
    -0.74
     DRAG
    -0.74
    POSITIVE LOGITS
    banks
    0.97
     encamp
    0.94
    bris
    0.88
    giene
    0.82
    yssey
    0.81
    lishing
    0.81
     beh
    0.81
    opolis
    0.79
     Cologne
    0.79
    iens
    0.79
    Activations Density 0.465%

    No Known Activations