© 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. 3-RES-JB
    11. 1970
    Prev
    Next
    INDEX
    Explanations

    names of persons or entities, particularly those related to legal or criminal contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or their roles or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -1.01
    acebook
    -0.76
    clud
    -0.71
    ciating
    -0.64
    eenth
    -0.64
     Fou
    -0.63
     Gazette
    -0.63
     Eliot
    -0.60
    UME
    -0.59
    urities
    -0.59
    POSITIVE LOGITS
    rors
    0.99
    idge
    0.96
    lein
    0.94
    ger
    0.87
    unning
    0.86
    baum
    0.85
    jee
    0.85
    lich
    0.85
    nery
    0.85
    aton
    0.84
    Activations Density 0.037%

    No Known Activations