© 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 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. 8-RES-JB
    11. 19283
    Prev
    Next
    INDEX
    Explanations

    the word "fork" in different contexts, primarily in relation to technical or physical objects rather than food

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "forks" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agna
    -0.72
     Coliseum
    -0.67
    useum
    -0.65
     Neville
    -0.62
    ences
    -0.61
     Madden
    -0.61
     Scotia
    -0.60
    anyahu
    -0.60
     Alam
    -0.59
    ered
    -0.59
    POSITIVE LOGITS
    lift
    1.51
    edIn
    0.97
    ingen
    0.92
    nect
    0.89
    crew
    0.88
    ansas
    0.83
    ners
    0.81
    nown
    0.81
    walk
    0.79
    fork
    0.76
    Activations Density 0.049%

    No Known Activations