© 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. 10-RES-JB
    11. 10465
    Prev
    Next
    INDEX
    Explanations

    pronouns with accompanying verbs suggesting decision-making or action

    oai_token-act-pair · gpt-3.5-turbo

    the use of the pronoun "we" and its variants in rhetorical questions

    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
    produced
    -0.69
    76561
    -0.67
    edIn
    -0.64
    uces
    -0.64
    ces
    -0.63
    ventures
    -0.63
    renheit
    -0.62
    operated
    -0.62
    ooks
    -0.62
    perties
    -0.61
    POSITIVE LOGITS
     ever
    1.11
     EVER
    1.07
     expect
    0.99
    ?
    0.97
    ?'
    0.96
     dare
    0.96
     succeed
    0.95
    ?'"
    0.92
    ?).
    0.90
     hesitate
    0.90
    Activations Density 0.065%

    No Known Activations