© 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. 7-RES-JB
    11. 5159
    Prev
    Next
    INDEX
    Explanations

    the names and political affiliations of politicians

    oai_token-act-pair · gpt-3.5-turbo

    parenthetical notation, particularly in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lull
    -0.84
     abduct
    -0.82
     drift
    -0.76
     ransom
    -0.74
     maturity
    -0.73
     smugglers
    -0.73
     assumptions
    -0.73
     parity
    -0.72
     spir
    -0.72
     equival
    -0.72
    POSITIVE LOGITS
    pictured
    1.51
    formerly
    1.29
    whose
    1.25
    who
    1.22
    aka
    1.13
    also
    1.07
    above
    1.05
    better
    1.04
    pron
    1.01
    among
    1.00
    Activations Density 0.077%

    No Known Activations