© 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. 8-RES-JB
    11. 7101
    Prev
    Next
    INDEX
    Explanations

    phrases expressing gratitude or excitement for a situation, achievement, or role

    oai_token-act-pair · gpt-3.5-turbo

    expressions of existence or being

    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
    rones
    -0.72
     rigs
    -0.69
    plings
    -0.68
     preparations
    -0.68
     strain
    -0.66
     dispute
    -0.66
     strains
    -0.65
     Prescott
    -0.65
     reconstruction
    -0.63
    itures
    -0.63
    POSITIVE LOGITS
     able
    1.28
     reminded
    0.90
     bitten
    0.89
     judged
    0.89
    leeve
    0.88
    league
    0.88
     entertained
    0.86
    auc
    0.85
     aware
    0.85
     reunited
    0.85
    Activations Density 0.115%

    No Known Activations