© 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 Local
    9. 6-RES_SCL-AJT
    11. 46043
    Prev
    Next
    INDEX
    Explanations

    options for customization in software or settings

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.20
    1.0%
    237
    +0.09
    0.5%
    70
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    738
    +0.20
    0.08
    227
    +0.09
    0.04
    70
    +0.09
    0.13
    Negative Logits
    oil
    -0.79
    Proof
    -0.66
    860
    -0.63
    Truth
    -0.62
    Hart
    -0.61
    ç«
    -0.60
     Irving
    -0.60
    roots
    -0.60
    NY
    -0.60
    ãĤ¬
    -0.59
    POSITIVE LOGITS
     customize
    1.16
     customizable
    0.94
     custom
    0.92
     customization
    0.92
     individually
    0.89
     customized
    0.88
     freely
    0.85
     presets
    0.84
     manually
    0.83
     preset
    0.80
    Activations Density 15.742%

    No Known Activations