© 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. 6-RES-JB
    11. 5149
    Prev
    Next
    INDEX
    Explanations

    concept art elements within text

    oai_token-act-pair · gpt-3.5-turbo

    references to visual art and artistic concepts

    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
    olean
    -0.79
    cffff
    -0.72
    edience
    -0.71
    Ń·
    -0.70
    phrine
    -0.69
    ;;;;;;;;;;;;
    -0.69
     Crosby
    -0.67
    ership
    -0.67
    hood
    -0.65
    ighed
    -0.65
    POSITIVE LOGITS
    emis
    1.17
    ifacts
    1.10
    works
    1.05
    isans
    1.01
    istry
    1.01
    Artist
    0.95
    work
    0.92
    board
    0.92
    heet
    0.91
     depicting
    0.91
    Activations Density 0.024%

    No Known Activations