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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4-RES-JB
    6. 17505
    Prev
    Next
    INDEX
    Explanations

    references to specific bills and legislative acts

    oai_token-act-pair · gpt-3.5-turbo

    references to legislative bills in Texas, specifically those labeled with "HB"

    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
    istically
    -0.80
     rall
    -0.71
     Earthqu
    -0.70
    ========
    -0.67
    pmwiki
    -0.67
    PsyNetMessage
    -0.64
     Tradable
    -0.64
     Samoa
    -0.64
    coni
    -0.64
    FTWARE
    -0.62
    POSITIVE LOGITS
    Gary
    1.06
    HB
    1.05
    KB
    0.88
     HB
    0.80
    heit
    0.79
    acking
    0.79
    ¶ħ
    0.75
    iencies
    0.74
    ugg
    0.72
    iff
    0.71
    Activations Density 0.012%

    No Known Activations