© 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. 10-RES-JB
    11. 7238
    Prev
    Next
    INDEX
    Explanations

    phrases related to individuals finding themselves in certain situations

    oai_token-act-pair · gpt-3.5-turbo

    reflexive pronouns and related phrases indicating self-reference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aic
    -0.68
    alez
    -0.67
    hide
    -0.64
    hee
    -0.63
     Plans
    -0.62
    omy
    -0.61
    beta
    -0.61
    rium
    -0.61
     Lancet
    -0.61
     Publication
    -0.60
    POSITIVE LOGITS
     embroiled
    1.29
     needing
    1.16
     wondering
    1.11
     entangled
    1.08
     stranded
    1.07
     unable
    1.07
     trapped
    1.05
     surrounded
    1.05
     engulfed
    1.01
     staring
    1.00
    Activations Density 0.038%

    No Known Activations