© 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. 17103
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically company names and products

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of commas in text

    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
    ipment
    -0.67
    aughter
    -0.67
    genic
    -0.67
    utive
    -0.63
    ategor
    -0.63
    ighed
    -0.61
    ported
    -0.61
    escription
    -0.60
    robe
    -0.60
    eni
    -0.60
    POSITIVE LOGITS
     but
    0.94
     whose
    0.92
     etc
    0.92
     although
    0.90
     which
    0.89
     nor
    0.87
     whereas
    0.86
     insofar
    0.83
     aka
    0.80
     except
    0.80
    Activations Density 0.295%

    No Known Activations