© 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. 17673
    Prev
    Next
    INDEX
    Explanations

    phrases related to fighting, challenges, and conflicts

    oai_token-act-pair · gpt-3.5-turbo

    themes related to fighting, struggles, and conflict

    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
    DATA
    -0.73
     Laksh
    -0.69
    OSP
    -0.66
    ITNESS
    -0.65
    ocument
    -0.64
     Oops
    -0.64
    gement
    -0.63
    rection
    -0.63
    ascript
    -0.63
     Address
    -0.62
    POSITIVE LOGITS
     uphill
    1.19
    against
    1.13
     against
    1.12
     battles
    1.09
     waged
    1.02
     attrition
    0.98
     valiant
    0.93
     Against
    0.92
    enegger
    0.91
     vain
    0.88
    Activations Density 0.388%

    No Known Activations