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

    Neuronpedia

    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. 13341
    Prev
    Next
    INDEX
    Explanations

    units of measurement related to distances

    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
    238
    +0.14
    0.5%
    23
    +0.14
    0.5%
    570
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    238
    +0.14
    0.06
    537
    +0.14
    0.06
    460
    +0.13
    0.05
    Negative Logits
    eer
    -1.04
    udeb
    -1.03
    analysis
    -0.96
    oly
    -0.93
    actionDate
    -0.92
    icer
    -0.88
    icent
    -0.87
    lez
    -0.86
    amac
    -0.86
    ubuntu
    -0.86
    POSITIVE LOGITS
     tall
    1.19
     diameter
    1.17
     separating
    1.05
     kilometers
    1.04
     meters
    1.01
     elevation
    1.00
     distance
    0.96
     thick
    0.93
    iameter
    0.92
     (~
    0.91
    Activations Density 0.530%

    No Known Activations