© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 1705
    Prev
    Next
    INDEX
    Explanations

    terms related to forming a conclusion or a decision, possibly in a discussion or debate

    oai_token-act-pair · gpt-3.5-turbo

    categorical claims or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    resso
    -0.72
    itter
    -0.68
    izoph
    -0.67
     Sandra
    -0.66
    apixel
    -0.65
    psey
    -0.65
    ID
    -0.64
     Database
    -0.62
     Tuls
    -0.61
     Lerner
    -0.61
    POSITIVE LOGITS
    saf
    0.79
    */(
    0.76
    rule
    0.73
    generic
    0.70
    thumbnails
    0.70
    obin
    0.66
    danger
    0.65
    conom
    0.65
    hazard
    0.65
    agonists
    0.64
    Activations Density 0.000%

    No Known Activations