© 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. 8-RES-JB
    11. 6841
    Prev
    Next
    INDEX
    Explanations

    images with captions

    oai_token-act-pair · gpt-3.5-turbo

    references to specific images or visual elements

    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
    bats
    -0.66
    apo
    -0.65
    APD
    -0.65
    uality
    -0.60
    naires
    -0.59
    Sund
    -0.59
    poke
    -0.59
    Jet
    -0.58
     Schwar
    -0.58
    uls
    -0.57
    POSITIVE LOGITS
     toggle
    0.98
     image
    0.88
     thumbnail
    0.82
     screenshot
    0.81
     WATCHED
    0.79
     photo
    0.79
     microscope
    0.78
     ARTICLE
    0.78
     Image
    0.77
     transcript
    0.76
    Activations Density 0.013%

    No Known Activations