© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 158
    Prev
    Next
    INDEX
    Explanations

    phrases related to someone's behaviors or actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of various actions being referenced or discussed

    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
    bid
    -0.72
    ickets
    -0.68
     Dise
    -0.68
    MAL
    -0.65
    orf
    -0.63
    ondo
    -0.63
    BLE
    -0.62
    population
    -0.62
    ringe
    -0.62
     AES
    -0.61
    POSITIVE LOGITS
    uations
    1.06
     actions
    1.00
     ACTIONS
    0.94
    uate
    0.91
    uation
    0.89
    uits
    0.88
    uated
    0.84
    uary
    0.82
    uating
    0.81
    hops
    0.80
    Activations Density 0.023%

    No Known Activations