© 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 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. 10803
    Prev
    Next
    INDEX
    Explanations

    references to actions of securing a note or message

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating comparisons or associations

    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
    erest
    -0.73
    oller
    -0.72
    lez
    -0.71
    stall
    -0.68
    hal
    -0.65
    order
    -0.63
    tail
    -0.62
    onse
    -0.61
    Enlarge
    -0.61
    gang
    -0.61
    POSITIVE LOGITS
     evidenced
    1.47
     well
    0.97
     opposed
    0.95
     soon
    0.89
     regards
    0.89
    phy
    0.87
     shown
    0.84
    pects
    0.84
     depicted
    0.80
     illustrated
    0.80
    Activations Density 0.132%

    No Known Activations