© 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. 10-RES-JB
    11. 2803
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or activities being initiated or undertaken by someone

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating actions or initiatives taken by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     appreciated
    -0.70
    icka
    -0.70
    ivas
    -0.65
    window
    -0.63
    STON
    -0.61
    enery
    -0.61
    orum
    -0.60
    chio
    -0.60
    pport
    -0.60
    phies
    -0.59
    POSITIVE LOGITS
     drastic
    0.87
     devised
    0.86
     ingenious
    0.84
     resorted
    0.82
     hastily
    0.82
     frantically
    0.78
     instead
    0.77
     unorthodox
    0.71
     Craigslist
    0.71
     concoct
    0.71
    Activations Density 0.437%

    No Known Activations