© 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. 18730
    Prev
    Next
    INDEX
    Explanations

    text related to industries and economic activities

    oai_token-act-pair · gpt-3.5-turbo

    combinations of commas and phrases that indicate lists or multiple subjects

    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
    minster
    -0.54
    ¬¼
    -0.54
    venth
    -0.53
    Override
    -0.50
    Thumbnail
    -0.50
    ãĥ¥
    -0.49
    prise
    -0.49
    rup
    -0.48
    pec
    -0.48
    ãĤĬ
    -0.46
    POSITIVE LOGITS
     wherein
    0.83
     namely
    0.80
     respectively
    0.77
     culminating
    0.77
     whereby
    0.74
     including
    0.72
     huh
    0.71
     although
    0.69
     but
    0.68
     whereas
    0.67
    Activations Density 0.434%

    No Known Activations