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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 17753
    Prev
    Next
    INDEX
    Explanations

    images or photographs

    oai_token-act-pair · gpt-3.5-turbo

    references to images

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    merce
    -0.86
    laws
    -0.86
    unts
    -0.83
    unin
    -0.76
    uckle
    -0.74
    rieg
    -0.73
    etheless
    -0.72
    bye
    -0.72
    sole
    -0.72
    tons
    -0.72
    POSITIVE LOGITS
     caption
    1.07
     Image
    1.06
    gallery
    0.99
     Gallery
    0.94
     Thumbnails
    0.90
    ################
    0.87
     Caption
    0.86
     Images
    0.84
    Images
    0.83
     Album
    0.81
    Activations Density 0.013%

    No Known Activations