© 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. 9-RES-JB
    11. 23781
    Prev
    Next
    INDEX
    Explanations

    prominent or well-established individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating expertise or reputation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ifacts
    -0.74
     Puzzles
    -0.65
     iPads
    -0.64
     alternatives
    -0.62
     unsafe
    -0.62
     scenarios
    -0.61
     versus
    -0.61
     Haram
    -0.60
     constraints
    -0.60
     simulations
    -0.59
    POSITIVE LOGITS
     lieutenant
    1.02
     outspoken
    0.97
    former
    0.93
    father
    0.92
    founder
    0.91
     renowned
    0.91
     dancer
    0.91
    ographer
    0.90
     theorist
    0.89
     eldest
    0.89
    Activations Density 0.344%

    No Known Activations