© 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. 9-RES-JB
    11. 1547
    Prev
    Next
    INDEX
    Explanations

    specific keywords related to technical jargon or industry-specific terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical data or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ican
    -0.61
    igslist
    -0.57
    oise
    -0.56
    apple
    -0.56
     helicop
    -0.55
    pring
    -0.53
    arial
    -0.53
    yahoo
    -0.52
    POL
    -0.52
    gmail
    -0.50
    POSITIVE LOGITS
     its
    0.65
    é¾įåĸļ士
    0.58
    hov
    0.58
    interrupted
    0.57
    taboola
    0.56
    rompt
    0.55
    ppings
    0.53
    juries
    0.53
     lockout
    0.52
    verty
    0.50
    Activations Density 1.619%

    No Known Activations