© 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. 21479
    Prev
    Next
    INDEX
    Explanations

    actions or activities described with a duration

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "for" followed by varying lengths of time or description

    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
    istle
    -0.67
    Ver
    -0.66
    inese
    -0.66
    venants
    -0.62
    ashtra
    -0.62
    haus
    -0.61
     Subscribe
    -0.61
    ivil
    -0.60
    VC
    -0.60
    fleet
    -0.60
    POSITIVE LOGITS
     awhile
    1.20
     hours
    1.15
     laughs
    1.06
     weeks
    0.98
     eternity
    0.97
     emphasis
    0.94
     dear
    0.94
     warmth
    0.93
    agers
    0.92
     days
    0.92
    Activations Density 0.154%

    No Known Activations