© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 20118
    Prev
    Next
    INDEX
    Explanations

    statements of outcomes or results

    oai_token-act-pair · gpt-3.5-turbo

    symbols or characters that indicate a specific context or interpretation, potentially related to emotional or impactful themes

    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
    enta
    -0.74
    lda
    -0.72
    itably
    -0.71
    vt
    -0.65
    oner
    -0.63
     patched
    -0.61
     coast
    -0.61
     sled
    -0.61
     scatter
    -0.60
     dig
    -0.60
    POSITIVE LOGITS
    âĹ¼
    0.97
    catentry
    0.92
    drivers
    0.82
    ¬
    0.81
    âģ
    0.81
    âĢł
    0.80
    ISIS
    0.79
    ¹
    0.77
    bryce
    0.76
    Footnote
    0.74
    Activations Density 0.563%

    No Known Activations