© 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. 12964
    Prev
    Next
    INDEX
    Explanations

    phrases related to impressive or impactful events or actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to 'impact' or significant effects

    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
    creen
    -1.05
    ãģ®éŃĶ
    -0.84
    halla
    -0.76
    Downloadha
    -0.75
    çĦ
    -0.75
    EngineDebug
    -0.69
    mberg
    -0.69
    yards
    -0.68
    ãģķ
    -0.67
    RAFT
    -0.66
    POSITIVE LOGITS
    acts
    1.12
    ressive
    1.05
    aired
    1.05
    ulse
    1.00
    actor
    0.99
    ression
    0.95
    regn
    0.95
    acet
    0.90
    ossible
    0.88
    ossibly
    0.87
    Activations Density 0.009%

    No Known Activations