© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10253
    Prev
    Next
    INDEX
    Explanations

    words related to criticisms or negative evaluations about something

    oai_token-act-pair · gpt-3.5-turbo

    words related to absurdity or ridiculousness

    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
     QC
    -0.63
    maker
    -0.61
    wo
    -0.60
     maker
    -0.59
     Pwr
    -0.59
     Ta
    -0.59
    nova
    -0.58
    bilt
    -0.57
    quart
    -0.57
     Brow
    -0.57
    POSITIVE LOGITS
    ulated
    1.12
    inate
    1.12
    ulation
    1.10
    inating
    1.10
    inatory
    1.10
    ulous
    1.09
    idity
    1.09
    idation
    1.07
    ination
    1.06
    inated
    1.06
    Activations Density 0.134%

    No Known Activations