© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11300
    Prev
    Next
    INDEX
    Explanations

    instances where a payment or financial transaction is involved

    oai_token-act-pair · gpt-3.5-turbo

    elements related to government actions and decisions

    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
     coworkers
    -0.66
     teammate
    -0.65
    die
    -0.63
    nen
    -0.62
    tein
    -0.61
     linem
    -0.58
    pload
    -0.58
    CTV
    -0.56
     mos
    -0.56
    ski
    -0.55
    POSITIVE LOGITS
     itself
    0.82
     its
    0.80
    arthed
    0.75
     theirs
    0.74
    glers
    0.67
     them
    0.64
     grants
    0.64
    erous
    0.63
     XD
    0.63
     prosecuting
    0.63
    Activations Density 0.668%

    No Known Activations