© 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. 4-RES-JB
    11. 6969
    Prev
    Next
    INDEX
    Explanations

    references to political figures, such as lawmakers and councillors

    oai_token-act-pair · gpt-3.5-turbo

    references to lawmakers and their roles

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

    No Comments

    Negative Logits
    avers
    -0.91
    awks
    -0.84
     Timbers
    -0.78
    ilers
    -0.77
    arus
    -0.77
    hens
    -0.76
    word
    -0.73
    tern
    -0.71
    ources
    -0.70
    imm
    -0.70
    POSITIVE LOGITS
     laureate
    0.78
    Joined
    0.67
     MLA
    0.67
     councillor
    0.66
     Franch
    0.66
     senator
    0.66
     extraord
    0.66
     CTR
    0.62
    nered
    0.61
     HUN
    0.61
    Activations Density 0.036%

    No Known Activations