© 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. 6990
    Prev
    Next
    INDEX
    Explanations

    references to the name "Ryan" in the text

    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
    247
    +0.26
    0.9%
    346
    +0.15
    0.5%
    187
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    247
    +0.26
    0.10
    352
    +0.15
    0.09
    154
    +0.13
    0.09
    Negative Logits
    oslav
    -1.05
     Seym
    -0.98
    CLASSIFIED
    -0.96
     hypers
    -0.95
    oscope
    -0.89
    sembly
    -0.89
     Sorceress
    -0.87
    osate
    -0.85
    Variable
    -0.84
     surv
    -0.84
    POSITIVE LOGITS
    air
    1.04
    ufact
    1.03
    ager
    1.02
    zona
    1.02
    aging
    1.01
    roll
    0.98
     Zin
    0.97
    airs
    0.97
     Gos
    0.96
    burn
    0.96
    Activations Density 2.360%

    No Known Activations