© 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. 12757
    Prev
    Next
    INDEX
    Explanations

    the word 'use'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "use" and its variations in different contexts

    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
    hoff
    -0.72
    si
    -0.68
    owship
    -0.66
    iae
    -0.66
    soon
    -0.64
    cellence
    -0.64
    pton
    -0.64
    watching
    -0.63
    ikhail
    -0.62
    orld
    -0.62
    POSITIVE LOGITS
    fully
    1.09
     condoms
    0.96
     aliases
    0.95
    FUL
    0.89
     contraceptives
    0.86
    ful
    0.86
     computers
    0.85
     them
    0.83
     tools
    0.83
     caution
    0.78
    Activations Density 0.101%

    No Known Activations