© 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. 3503
    Prev
    Next
    INDEX
    Explanations

    printable recipes or instructions

    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
    278
    +0.13
    0.5%
    679
    +0.12
    0.5%
    758
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.13
    0.04
    311
    +0.12
    0.00
    373
    +0.12
    -0.03
    Negative Logits
    hu
    -0.79
    osc
    -0.76
    fell
    -0.72
    chnology
    -0.70
    rast
    -0.68
    OGR
    -0.67
    hair
    -0.67
    ··
    -0.66
    È
    -0.65
     GOT
    -0.65
    POSITIVE LOGITS
     Calories
    0.94
     Template
    0.86
     Awareness
    0.76
    Slow
    0.74
    Template
    0.73
    ertodd
    0.71
     Tags
    0.71
    odium
    0.70
     Friendly
    0.70
     Serving
    0.69
    Activations Density 0.243%

    No Known Activations