© 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. 6857
    Prev
    Next
    INDEX
    Explanations

    sentences about actions or events that have been done to someone or something

    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
    508
    +0.15
    0.5%
    499
    +0.13
    0.5%
    709
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    217
    +0.15
    0.05
    499
    +0.13
    0.04
    197
    +0.13
    0.04
    Negative Logits
    ullivan
    -0.94
    itect
    -0.92
    psc
    -0.90
    Arg
    -0.85
    ierre
    -0.84
    uder
    -0.83
    velt
    -0.82
    asm
    -0.82
    tra
    -0.81
    tenance
    -0.80
    POSITIVE LOGITS
    aways
    1.28
    away
    1.13
    bread
    1.09
     precedence
    1.05
    tering
    1.00
    mint
    0.99
    esville
    0.99
    chy
    0.98
    ãĥį
    0.98
    ãĥ¼ãĥĨ
    0.97
    Activations Density 0.361%

    No Known Activations