© 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. 9-RES-JB
    11. 1971
    Prev
    Next
    INDEX
    Explanations

    references to political and social issues, discussions, and decisions

    oai_token-act-pair · gpt-3.5-turbo

    references to collective actions and the use of "we" in discussions about societal issues

    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
    aults
    -0.73
     Rowe
    -0.68
    REDACTED
    -0.65
    amina
    -0.64
    imum
    -0.59
    cum
    -0.59
     Kush
    -0.59
     Publication
    -0.59
     Spec
    -0.58
    imo
    -0.58
    POSITIVE LOGITS
    akening
    1.22
    're
    1.21
    've
    1.19
     shouldn
    1.12
     owe
    1.11
     ought
    1.04
     need
    1.02
     ourselves
    1.02
     cannot
    1.01
    asel
    1.01
    Activations Density 0.206%

    No Known Activations