© 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. 9-RES-JB
    11. 7104
    Prev
    Next
    INDEX
    Explanations

    political topics and actions

    oai_token-act-pair · gpt-3.5-turbo

    actions and political decisions involving influential figures or authorities

    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
     totaled
    -0.62
    enery
    -0.60
     multiplied
    -0.59
     Username
    -0.59
     WATCHED
    -0.58
     classmates
    -0.58
    inguished
    -0.56
     span
    -0.56
     âĶľâĶĢâĶĢ
    -0.56
     manif
    -0.55
    POSITIVE LOGITS
     reconsider
    0.91
     outright
    0.88
     unilaterally
    0.86
     anytime
    0.84
     anything
    0.78
     capit
    0.78
    urther
    0.77
     unilateral
    0.76
     any
    0.74
    enance
    0.73
    Activations Density 0.551%

    No Known Activations