© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 7608
    Prev
    Next
    INDEX
    Explanations

    mentions or instances of images

    oai_token-act-pair · gpt-3.5-turbo

    references to images or visual content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     furn
    -0.72
     score
    -0.71
     tob
    -0.71
     sheets
    -0.68
     suicides
    -0.67
     table
    -0.66
     chat
    -0.66
     rag
    -0.66
     detective
    -0.65
     plot
    -0.65
    POSITIVE LOGITS
    image
    3.46
    images
    1.72
    digit
    1.33
    application
    1.33
    gment
    1.16
    position
    1.12
    headers
    1.12
    thought
    1.11
    vision
    1.10
    Image
    1.07
    Activations Density 0.021%

    No Known Activations