© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 634
    Prev
    Next
    INDEX
    Explanations

    phrases containing ellipses indicating omitted text in journalistic contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of ellipses or fragmented text indicating omitted content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    meg
    -0.85
    anooga
    -0.83
    itud
    -0.77
    icum
    -0.76
    onite
    -0.76
    ista
    -0.75
    aeus
    -0.74
    agar
    -0.73
    amins
    -0.73
    aho
    -0.73
    POSITIVE LOGITS
    ...]
    0.95
    ³³³³³³³³
    0.89
    ³³³³³³³³³³³³³³³³
    0.85
    ³³³
    0.76
    ptives
    0.76
     [...]
    0.74
    ploy
    0.74
    âĹ¼
    0.73
    CLASSIFIED
    0.73
     FINAL
    0.71
    Activations Density 0.009%

    No Known Activations