© 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. 3727
    Prev
    Next
    INDEX
    Explanations

    words related to printing or physical production

    oai_token-act-pair · gpt-3.5-turbo

    terms related to food preparation and printing processes

    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
    fully
    -0.77
    ledge
    -0.72
    ably
    -0.71
    adra
    -0.68
    ned
    -0.65
    adan
    -0.62
    eda
    -0.61
    pered
    -0.61
    went
    -0.60
     levied
    -0.60
    POSITIVE LOGITS
    escription
    0.94
     goods
    0.87
    ness
    0.87
    own
    0.87
    paren
    0.86
    ouble
    0.79
    river
    0.76
     versions
    0.75
    ancer
    0.74
    iatrics
    0.71
    Activations Density 0.244%

    No Known Activations