© 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. 4-RES-JB
    11. 15321
    Prev
    Next
    INDEX
    Explanations

    mentions of the state of Washington

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of "Washington State."

    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
    INAL
    -0.86
     Donation
    -0.74
     (<
    -0.72
    ONY
    -0.71
    ogram
    -0.69
     guiActiveUnfocused
    -0.68
    Champ
    -0.67
    rophe
    -0.67
    resso
    -0.66
    risis
    -0.66
    POSITIVE LOGITS
    ipeg
    0.68
    flix
    0.65
     circles
    0.64
    wagen
    0.63
    ockets
    0.63
     tether
    0.63
     avenue
    0.63
    schild
    0.62
    çİĭ
    0.62
     Kashmir
    0.62
    Activations Density 0.113%

    No Known Activations