© 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. 8-RES-JB
    11. 17242
    Prev
    Next
    INDEX
    Explanations

    paragraph breaks followed by an indication to read more content

    oai_token-act-pair · gpt-3.5-turbo

    ellipses or omitted content in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oche
    -0.74
    ally
    -0.71
     suspic
    -0.71
    ially
    -0.71
    itude
    -0.70
    ²¾
    -0.69
     nomine
    -0.68
    ratulations
    -0.68
    hematically
    -0.68
    itably
    -0.67
    POSITIVE LOGITS
     Appears
    0.92
     âĢİ
    0.85
     Continue
    0.78
     Author
    0.74
     Posted
    0.73
     READ
    0.71
     Bride
    0.71
     Written
    0.69
     Retrieved
    0.68
     Read
    0.66
    Activations Density 0.063%

    No Known Activations