© 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. 6-RES-JB
    11. 24468
    Prev
    Next
    INDEX
    Explanations

    instances of the word "revision" or its variants

    oai_token-act-pair · gpt-3.5-turbo

    mentions of revisions or updates to existing standards, regulations, or policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esm
    -0.70
    gdala
    -0.70
    asia
    -0.68
    Phones
    -0.68
    Craft
    -0.66
    ech
    -0.65
     Mellon
    -0.65
    ecause
    -0.62
     Winged
    -0.62
    lehem
    -0.62
    POSITIVE LOGITS
     revision
    0.91
     revisions
    0.79
     retrospect
    0.78
    itized
    0.77
     formulations
    0.71
     guiActiveUn
    0.71
     Revision
    0.69
     drafts
    0.66
     chronological
    0.66
    aution
    0.66
    Activations Density 0.013%

    No Known Activations