© 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. 1-RES-JB
    11. 10282
    Prev
    Next
    INDEX
    Explanations

    the word "any" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    the word "any" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rex
    -0.71
    rez
    -0.67
    appings
    -0.65
    bows
    -0.64
    ros
    -0.61
    iano
    -0.61
    ades
    -0.61
    seless
    -0.60
    endas
    -0.59
    expensive
    -0.58
    POSITIVE LOGITS
    THING
    1.22
     conceivable
    0.94
    thin
    0.91
    body
    0.91
    WHERE
    0.91
    where
    0.89
    ONE
    0.83
     else
    0.79
     imaginable
    0.77
     remotely
    0.73
    Activations Density 0.056%

    No Known Activations