© 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. 1698
    Prev
    Next
    INDEX
    Explanations

    phrases related to organizations, industries, and actions or events involving them

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "which" and its associations with subjects and industries, indicating a focus on clarifying or elaborating on previous statements

    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
    Vari
    -0.74
    Untitled
    -0.69
    Translation
    -0.64
    ANY
    -0.64
    unknown
    -0.63
     Passage
    -0.63
    construct
    -0.63
    roy
    -0.60
    rossover
    -0.59
    IDENT
    -0.58
    POSITIVE LOGITS
     notoriously
    1.10
     traditionally
    1.05
     desperately
    1.05
     relies
    1.02
     sorely
    0.98
     routinely
    0.97
     famously
    0.95
     perenn
    0.94
     admittedly
    0.94
     struggled
    0.93
    Activations Density 0.307%

    No Known Activations