© 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. 8-RES-JB
    11. 20197
    Prev
    Next
    INDEX
    Explanations

    descriptions related to providing information or guidance for making decisions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to hesitation or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UTC
    -0.66
    ".[
    -0.65
    .[
    -0.64
    ."[
    -0.62
    ©¶æ¥µ
    -0.61
     âĶľ
    -0.59
     '.
    -0.58
    render
    -0.58
    til
    -0.58
    nown
    -0.57
    POSITIVE LOGITS
     yourself
    0.82
     please
    0.71
     blogging
    0.66
     podcasts
    0.62
     anymore
    0.61
     beginner
    0.61
    entious
    0.61
     Yourself
    0.60
     stocking
    0.60
     inspiration
    0.59
    Activations Density 0.442%

    No Known Activations