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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-RES-JB
    6. 20088
    Prev
    Next
    INDEX
    Explanations

    references to sources of bright light such as flashlights, flashbang grenades, and flash floods

    oai_token-act-pair · gpt-3.5-turbo

    references to "flash" in various contexts, including sales, light, and media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ally
    -0.80
    ufact
    -0.66
     Dame
    -0.65
     Alban
    -0.64
    ality
    -0.63
    aples
    -0.60
    amins
    -0.60
    essen
    -0.58
     atmosp
    -0.58
     Tonight
    -0.57
    POSITIVE LOGITS
    bang
    1.20
    points
    1.18
    mob
    1.16
    lights
    1.15
    point
    1.13
    light
    1.12
    cards
    1.11
    fast
    1.02
    back
    0.99
    bul
    0.99
    Activations Density 0.060%

    No Known Activations