© 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. 10023
    Prev
    Next
    INDEX
    Explanations

    specific physical features or attributes described in text, such as "lid," "roof," and "graphic."

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to architectural and structural components

    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
    ãģĹ
    -0.71
    cffff
    -0.65
    Demand
    -0.64
    PDATE
    -0.62
    ãģĻ
    -0.61
    actionDate
    -0.61
    puting
    -0.61
    Reporting
    -0.61
    KNOWN
    -0.60
     ILCS
    -0.60
    POSITIVE LOGITS
     depicts
    1.66
     contains
    1.59
     consists
    1.58
     resembles
    1.55
     comprises
    1.47
     incorporates
    1.37
     bears
    1.37
     corresponds
    1.35
     features
    1.34
     showcases
    1.34
    Activations Density 0.264%

    No Known Activations