© 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. 10-RES-JB
    11. 6948
    Prev
    Next
    INDEX
    Explanations

    keywords related to software development, particularly focusing on terms like "Dev", "iant", "art", and specific technical phrases like "/dev/null"

    oai_token-act-pair · gpt-3.5-turbo

    references to digital art and associated platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ogle
    -0.63
    osate
    -0.63
    CHO
    -0.60
    verty
    -0.60
     vulner
    -0.59
    Ô
    -0.58
    ĨĴ
    -0.58
    00200000
    -0.57
     grandma
    -0.57
    yip
    -0.57
    POSITIVE LOGITS
    ciating
    0.86
     Daniels
    0.72
    tails
    0.65
    rations
    0.65
     Kelley
    0.64
    medium
    0.63
    rers
    0.62
    monds
    0.62
    ãĤ¨ãĥ«
    0.60
    rences
    0.60
    Activations Density 0.151%

    No Known Activations