© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8912
    Prev
    Next
    INDEX
    Explanations

    long descriptive phrases related to trends or changes over time, with a specific focus on upward and downward movements

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.22
    0.7%
    141
    +0.16
    0.5%
    316
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.22
    0.08
    151
    +0.16
    0.06
    99
    +0.14
    0.05
    Negative Logits
    abase
    -1.25
    ghazi
    -1.20
    anan
    -1.13
    anca
    -1.12
    lez
    -1.10
    mberg
    -1.08
    acea
    -1.05
    ña
    -1.02
    ador
    -1.00
    ourke
    -0.99
    POSITIVE LOGITS
    ward
    1.34
    wards
    1.26
    ly
    1.21
     compatibility
    1.16
    dash
    1.10
     Bound
    1.09
    bound
    1.07
    vector
    1.05
     bound
    1.04
    Bound
    1.02
    Activations Density 0.926%

    No Known Activations