© 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. 1-RES-JB
    11. 13885
    Prev
    Next
    INDEX
    Explanations

    keywords related to distributing printed material, such as flyers, leaflets, brochures, and pamphlets

    oai_token-act-pair · gpt-3.5-turbo

    references to printed materials related to activism or information dissemination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ton
    -0.74
    ween
    -0.74
    hart
    -0.71
    vid
    -0.68
    atorial
    -0.68
     Mysteries
    -0.66
    Oracle
    -0.66
    Iv
    -0.66
    haul
    -0.65
     Commissioner
    -0.65
    POSITIVE LOGITS
     flyers
    1.55
     flyer
    1.39
     pamph
    1.31
     leaflets
    1.28
     posters
    1.15
     pamphlet
    1.13
     broch
    1.10
     indu
    0.93
     billboards
    0.87
     booklet
    0.86
    Activations Density 0.014%

    No Known Activations