© 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. 4-RES-JB
    11. 9104
    Prev
    Next
    INDEX
    Explanations

    keywords related to personal or public perception and reputation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "image."

    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
    ighter
    -0.93
    ighters
    -0.92
    aptic
    -0.86
    endez
    -0.85
    merce
    -0.82
    cffff
    -0.82
    ugs
    -0.81
    hurst
    -0.78
    ggles
    -0.78
    uum
    -0.78
    POSITIVE LOGITS
     caption
    1.01
     image
    0.93
     gallery
    0.87
     depicting
    0.85
    gallery
    0.82
     macros
    0.80
     representation
    0.80
     images
    0.78
     galleries
    0.77
     depiction
    0.76
    Activations Density 0.025%

    No Known Activations