© 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. 2540
    Prev
    Next
    INDEX
    Explanations

    photographs or images

    oai_token-act-pair · gpt-3.5-turbo

    references to photographs or imagery

    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
    ammy
    -0.72
     hearing
    -0.72
    rology
    -0.71
     busy
    -0.71
    lower
    -0.68
    die
    -0.67
     thorough
    -0.66
     devoted
    -0.65
     retard
    -0.64
    lda
    -0.62
    POSITIVE LOGITS
     Photograph
    1.60
     Thumbnails
    1.14
    ographs
    1.10
     Photographer
    1.10
     IMAGES
    1.02
    ograph
    0.97
     PHOTO
    0.93
    Phot
    0.91
     Images
    0.90
    ograms
    0.90
    Activations Density 0.005%

    No Known Activations