© 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. 14495
    Prev
    Next
    INDEX
    Explanations

    information and details that are being presented or discussed

    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
    195
    +0.17
    0.6%
    288
    +0.16
    0.6%
    320
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    642
    +0.17
    0.03
    320
    +0.16
    0.04
    195
    +0.14
    0.02
    Negative Logits
    si
    -0.92
    umph
    -0.92
    kowski
    -0.80
     msec
    -0.78
    imb
    -0.77
    leans
    -0.76
    leen
    -0.76
    heed
    -0.75
    meter
    -0.74
    lez
    -0.74
    POSITIVE LOGITS
    icts
    1.01
     presentations
    1.00
    eering
    0.99
    emonium
    0.97
    ħĭ
    0.94
    ¶æ
    0.94
    ICT
    0.92
    eers
    0.89
    ragon
    0.89
    encing
    0.88
    Activations Density 0.545%

    No Known Activations