© 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. 14666
    Prev
    Next
    INDEX
    Explanations

    technical words related to computer programming

    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
    482
    +0.15
    0.6%
    624
    +0.12
    0.5%
    712
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.15
    0.10
    128
    +0.12
    0.08
    659
    +0.12
    0.08
    Negative Logits
    eering
    -0.94
     PRESS
    -0.83
    WARE
    -0.82
    eers
    -0.81
    heid
    -0.77
     SYSTEM
    -0.73
    çĽ
    -0.71
    etheless
    -0.70
     Learns
    -0.69
    EngineDebug
    -0.69
    POSITIVE LOGITS
    atton
    1.18
    avour
    1.15
    iber
    1.07
    avia
    1.06
    ares
    1.01
    atz
    0.99
    acies
    0.99
    inks
    0.99
    avan
    0.99
    anners
    0.99
    Activations Density 1.161%

    No Known Activations