© 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. 2823
    Prev
    Next
    INDEX
    Explanations

    terms related to places or locations such as land, schools, streets, and cities

    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
    566
    +0.18
    0.6%
    202
    +0.17
    0.6%
    289
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.18
    0.05
    128
    +0.17
    0.05
    289
    +0.15
    0.02
    Negative Logits
    âĸ¬âĸ¬
    -1.19
    âĸ¬
    -1.09
    BOOK
    -1.04
    worthiness
    -1.00
    keeper
    -1.00
    bolt
    -1.00
    PRES
    -0.99
    bred
    -0.98
    Madison
    -0.97
    NESS
    -0.96
    POSITIVE LOGITS
    atter
    1.66
    umber
    1.49
    asma
    1.45
    umbers
    1.44
    utonium
    1.40
    aques
    1.40
    ump
    1.39
    iffs
    1.38
    acer
    1.38
    enium
    1.37
    Activations Density 0.888%

    No Known Activations