© 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. 6460
    Prev
    Next
    INDEX
    Explanations

    references to time periods in the middle of a range

    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
    649
    +0.17
    0.5%
    494
    +0.16
    0.5%
    496
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    607
    +0.17
    0.04
    616
    +0.16
    0.04
    494
    +0.15
    0.04
    Negative Logits
    edIn
    -1.24
     Bearing
    -1.04
    Magikarp
    -1.04
    ARDS
    -1.02
     Galileo
    -0.98
    éĹĺ
    -0.97
    Reviewed
    -0.95
     Pin
    -0.92
    itsch
    -0.91
    çİĭ
    -0.91
    POSITIVE LOGITS
    west
    1.33
    -'
    1.32
    western
    1.31
    terms
    1.31
    wives
    1.30
    cellaneous
    1.23
    ummer
    1.21
    wife
    1.19
    stad
    1.17
    century
    1.17
    Activations Density 0.521%

    No Known Activations