© 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. 11-RES-JB
    11. 11975
    Prev
    Next
    INDEX
    Explanations

    phrases related to legislation and policy

    oai_token-act-pair · gpt-3.5-turbo

    period-ending punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     carbohyd
    -0.94
     tremend
    -0.83
     volunte
    -0.80
     conclud
    -0.80
    ancies
    -0.74
     themselves
    -0.71
    elaide
    -0.70
    ascus
    -0.70
    emetery
    -0.69
     mosqu
    -0.69
    POSITIVE LOGITS
     Its
    2.33
     It
    1.79
    Its
    1.77
     Unlike
    1.33
     Designed
    1.21
     ITS
    1.17
     Whereas
    1.16
     Compared
    1.15
     Though
    1.15
     Originally
    1.14
    Activations Density 0.613%

    No Known Activations