© 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. 6-RES-JB
    11. 9777
    Prev
    Next
    INDEX
    Explanations

    headings or section separators in a document

    oai_token-act-pair · gpt-3.5-turbo

    lines and sections of text that are formatted as dividers or separators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rs
    -0.75
    UAL
    -0.69
    arters
    -0.68
    past
    -0.68
    gi
    -0.68
    flight
    -0.66
    sburg
    -0.64
    holders
    -0.64
    gio
    -0.64
    WAYS
    -0.64
    POSITIVE LOGITS
    odies
    0.91
    PsyNetMessage
    0.79
     "$:/
    0.77
    inated
    0.76
    ascus
    0.74
    inatory
    0.74
    ipolar
    0.72
    inished
    0.72
    ohydrate
    0.72
     Osw
    0.70
    Activations Density 0.087%

    No Known Activations