© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 7470
    Prev
    Next
    INDEX
    Explanations

    titles or mentions of the movie "Dawn of Justice"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Dawn" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ttle
    -0.85
    amins
    -0.78
    olicy
    -0.74
    uana
    -0.72
    ierrez
    -0.72
    natureconservancy
    -0.67
    onductor
    -0.67
    ribly
    -0.66
    atem
    -0.66
    odox
    -0.65
    POSITIVE LOGITS
    guard
    0.94
    walker
    0.92
    bringer
    0.90
    flower
    0.85
    yer
    0.84
    star
    0.83
    ing
    0.82
     Sparkle
    0.80
    bach
    0.80
    hurst
    0.78
    Activations Density 0.043%

    No Known Activations