Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 15346
    Prev
    Next
    INDEX
    Explanations

    captions related to images

    oai_token-act-pair · gpt-3.5-turbo

    references to photos in various contexts

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

    No Comments

    Negative Logits
    merce
    -0.83
     denomin
    -0.70
     congress
    -0.70
    iss
    -0.67
    mie
    -0.67
     stool
    -0.66
     gentleman
    -0.66
    antle
    -0.66
    ministic
    -0.65
     figure
    -0.65
    POSITIVE LOGITS
     Photos
    0.95
    Gallery
    0.90
     Caption
    0.89
     Thumbnails
    0.89
    Photos
    0.88
    ynthesis
    0.88
     Scenes
    0.82
    OTOS
    0.81
    =#
    0.79
    thumbnails
    0.78
    Activations Density 0.006%

    No Known Activations