© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 18485
    Prev
    Next
    INDEX
    Explanations

    proper nouns likely related to people or media titles such as "Will"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Will."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ħĭ
    -0.73
    MpServer
    -0.69
    antics
    -0.67
    ICAN
    -0.67
    ORPG
    -0.67
    quished
    -0.66
    Newsletter
    -0.66
    é¾įåĸļ士
    -0.64
     lion
    -0.64
    illin
    -0.63
    POSITIVE LOGITS
    power
    0.95
    ows
    0.92
    endor
    0.87
    kie
    0.86
    iam
    0.82
     Likely
    0.82
     Arn
    0.80
    ow
    0.77
    iston
    0.76
    liam
    0.72
    Activations Density 0.051%

    No Known Activations