© 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. 7701
    Prev
    Next
    INDEX
    Explanations

    past tense verbs indicating actions or events that happened

    oai_token-act-pair · gpt-3.5-turbo

    repetitive uses of the verb "got" in various contexts

    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
    NESS
    -0.69
     Archdemon
    -0.66
     Reprodu
    -0.63
    externalActionCode
    -0.63
    worthiness
    -0.61
     correctness
    -0.60
    margin
    -0.58
    ±
    -0.58
    Beginning
    -0.57
    orable
    -0.56
    POSITIVE LOGITS
     bored
    1.12
     booted
    1.08
     rid
    1.06
     sucked
    1.06
     bitten
    1.05
     pissed
    1.05
     married
    1.05
     robbed
    1.04
     caught
    1.04
     kicked
    1.04
    Activations Density 0.104%

    No Known Activations