© 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. 0-RES-JB
    11. 6617
    Prev
    Next
    INDEX
    Explanations

    phrases related to continuous or uninterrupted actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "stop" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     incorporated
    -0.68
     mould
    -0.67
     asc
    -0.63
     packs
    -0.61
     grav
    -0.61
     aff
    -0.61
     bos
    -0.60
     priv
    -0.60
     typ
    -0.60
     hol
    -0.60
    POSITIVE LOGITS
    stop
    4.43
    Stop
    2.29
     Stop
    1.98
     stop
    1.93
     STOP
    1.58
     stops
    1.54
    stay
    1.21
    lest
    1.14
    keep
    1.12
     halt
    1.11
    Activations Density 0.006%

    No Known Activations