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. 1-RES-JB
    6. 17113
    Prev
    Next
    INDEX
    Explanations

    regulations or orders related to specific entities or government agencies

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the acronym "SL" followed by numbers, indicating a focus on regulatory or safety directives related to surveillance laws

    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
    tainment
    -0.73
    raising
    -0.70
     Samar
    -0.66
    ruary
    -0.64
    ãĥ´ãĤ¡
    -0.63
    gerald
    -0.62
    actionDate
    -0.61
    ãĥį
    -0.60
    rendered
    -0.58
    nect
    -0.58
    POSITIVE LOGITS
    SL
    1.02
    ASH
    0.92
    ength
    0.92
    ashes
    0.84
    ibrary
    0.83
    OTS
    0.83
    VL
    0.83
    anguage
    0.83
    ashing
    0.80
    ash
    0.80
    Activations Density 0.004%

    No Known Activations