© 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. 11-RES-JB
    11. 705
    Prev
    Next
    INDEX
    Explanations

    a list of items or individuals that are associated with a shared category or description

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve multiple subjects or entities in a sentence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VERTISEMENT
    -0.78
    enza
    -0.68
    imeter
    -0.67
    rontal
    -0.64
    hower
    -0.64
    rid
    -0.63
    kill
    -0.62
    EngineDebug
    -0.62
    IDENT
    -0.61
    Usage
    -0.60
    POSITIVE LOGITS
    who
    1.63
     who
    1.62
     whom
    1.54
     retirees
    1.12
     whose
    1.10
    whose
    1.07
     spouses
    1.02
     businessmen
    0.99
     bloggers
    0.96
     educators
    0.94
    Activations Density 0.309%

    No Known Activations