© 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. 10236
    Prev
    Next
    INDEX
    Explanations

    professional or medical advice

    oai_token-act-pair · gpt-3.5-turbo

    quantifiers indicating frequency or quantity

    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
    ileaks
    -0.70
    SIGN
    -0.69
    multipl
    -0.68
    edin
    -0.68
    Balt
    -0.68
    Flag
    -0.65
    Alert
    -0.65
    ernaut
    -0.62
    hern
    -0.61
    cloneembedreportprint
    -0.61
    POSITIVE LOGITS
     countries
    1.04
     people
    1.03
     jurisdictions
    1.01
     situations
    0.97
     companies
    0.97
     individuals
    0.96
     manufacturers
    0.95
     cultures
    0.94
     types
    0.94
     societies
    0.92
    Activations Density 0.172%

    No Known Activations