© 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. 7016
    Prev
    Next
    INDEX
    Explanations

    phrases related to various specific topics, such as medical conditions, athletic events, financial situations, and technological details, among others

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating competitiveness or performance metrics

    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
    itton
    -0.57
     largeDownload
    -0.51
    rather
    -0.49
     assorted
    -0.49
    leted
    -0.49
    osen
    -0.48
    ismo
    -0.47
    onomy
    -0.47
    accompanied
    -0.46
    DragonMagazine
    -0.44
    POSITIVE LOGITS
     anymore
    1.81
     nor
    1.72
     anything
    1.22
     any
    1.19
     whatsoever
    1.13
     anywhere
    1.11
     slightest
    1.06
     anybody
    1.03
     necessarily
    1.03
    nor
    1.02
    Activations Density 1.621%

    No Known Activations