© 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. 10-RES-JB
    11. 8427
    Prev
    Next
    INDEX
    Explanations

    mentions of potential challenges, possibilities, or preparations for future events or decisions

    oai_token-act-pair · gpt-3.5-turbo
    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
    \'
    -0.78
    enery
    -0.77
    ographs
    -0.76
    Anim
    -0.75
    <?
    -0.73
    ombat
    -0.73
    Contents
    -0.72
    Statistics
    -0.71
    ontent
    -0.71
    wered
    -0.69
    POSITIVE LOGITS
     possible
    1.09
     showdown
    1.08
     future
    1.04
     fuller
    1.03
     comeback
    1.02
     forthcoming
    1.02
     revival
    1.01
     continuation
    1.01
     gradual
    1.00
     takeover
    0.99
    Activations Density 0.337%

    No Known Activations