© 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. 11-RES-JB
    11. 22546
    Prev
    Next
    INDEX
    Explanations

    words containing the suffix "-in" followed by a number, which may signify an intensity level or a specific action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "in" across 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
     McGill
    -0.71
     shake
    -0.63
     OMG
    -0.61
     launch
    -0.59
     DOI
    -0.58
     reckoned
    -0.58
     bye
    -0.57
     stakes
    -0.57
    ebin
    -0.56
     Miliband
    -0.55
    POSITIVE LOGITS
    strument
    1.84
    jury
    1.70
    visible
    1.64
    jured
    1.62
    iti
    1.61
    vasive
    1.57
    jected
    1.56
    clusive
    1.56
    flation
    1.54
    cluded
    1.54
    Activations Density 0.069%

    No Known Activations