© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 5690
    Prev
    Next
    INDEX
    Explanations

    statements or information related to detaining or detainers

    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
    178
    +0.16
    0.7%
    288
    +0.14
    0.6%
    356
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.10
    326
    +0.14
    0.07
    178
    +0.12
    0.06
    Negative Logits
    ocene
    -0.94
    xual
    -0.93
    ammy
    -0.92
    û
    -0.90
    otin
    -0.82
    inventoryQuantity
    -0.80
    intendent
    -0.80
    manship
    -0.79
    clerosis
    -0.76
    ÃŁ
    -0.76
    POSITIVE LOGITS
    rans
    1.13
    roit
    0.93
    ainers
    0.91
    achable
    0.89
    enance
    0.89
    NEY
    0.88
    ney
    0.88
    ENTION
    0.86
    rast
    0.85
    ention
    0.85
    Activations Density 1.112%

    No Known Activations