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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11351
    Prev
    Next
    INDEX
    Explanations

    numerical quantities or statistics

    oai_token-act-pair · gpt-3.5-turbo

    phrases introducing new information or significant statements

    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
    pleted
    -0.77
    thood
    -0.73
    )</
    -0.71
    Reviewer
    -0.70
    .","
    -0.69
    idth
    -0.69
    anga
    -0.68
    untarily
    -0.68
    acs
    -0.67
    ulu
    -0.66
    POSITIVE LOGITS
     discrepancy
    0.90
     troubling
    0.90
     predicament
    0.90
     contradiction
    0.90
     sentiments
    0.89
     rhetorical
    0.87
     sentiment
    0.86
     remarkable
    0.86
     dilemma
    0.86
     alarming
    0.85
    Activations Density 0.458%

    No Known Activations