© 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
    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. 22323
    Prev
    Next
    INDEX
    Explanations

    punctuation marks typically used for emphasis or organization

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and encoded characters often used in digital formatting

    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
     prest
    -0.49
    ãĤ©
    -0.47
     predec
    -0.46
     challeng
    -0.45
     destro
    -0.45
    ardless
    -0.45
    aturdays
    -0.45
     manif
    -0.44
     equivalents
    -0.43
    iqueness
    -0.43
    POSITIVE LOGITS
    CVE
    0.49
    LOS
    0.49
     REUTERS
    0.48
    humans
    0.48
     âĢº
    0.46
     Hide
    0.45
    UTERS
    0.44
    HOU
    0.44
     Scientists
    0.43
    SCP
    0.43
    Activations Density 1.041%

    No Known Activations