© 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. 18646
    Prev
    Next
    INDEX
    Explanations

    statements of acts being done repeatedly

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "repeatedly" and variations of expressions related to continuous actions or 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
    toc
    -0.75
    ellar
    -0.71
    arine
    -0.71
    emetery
    -0.69
    collection
    -0.68
    ghai
    -0.66
    early
    -0.66
    igans
    -0.66
    agra
    -0.65
    asus
    -0.64
    POSITIVE LOGITS
     denied
    0.93
     reiterated
    0.91
     unsuccessful
    0.90
     stressed
    0.89
     interrupted
    0.89
     reaff
    0.89
     voiced
    0.88
     reiter
    0.88
     emphasized
    0.87
     denounced
    0.85
    Activations Density 0.067%

    No Known Activations