© 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. 11-RES-JB
    11. 18522
    Prev
    Next
    INDEX
    Explanations

    pronouns, verbs, and relating terms associated with the concept of being broke

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "to be" in various forms

    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
    ð
    -0.90
    oire
    -0.89
    lished
    -0.79
    paralleled
    -0.76
    culosis
    -0.76
    osate
    -0.74
    ilege
    -0.74
    earance
    -0.73
    bernatorial
    -0.73
    ographer
    -0.72
    POSITIVE LOGITS
     idiots
    1.22
     selves
    1.09
     regulars
    1.09
    wolves
    1.07
     monsters
    1.03
     thugs
    1.03
     clones
    1.02
     ambassadors
    1.02
     professionals
    1.02
     mercenaries
    1.02
    Activations Density 0.280%

    No Known Activations