© 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 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. 10257
    Prev
    Next
    INDEX
    Explanations

    phrases expressing specificity and directness

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize exactness or specificity in descriptions

    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
    eka
    -0.77
    ways
    -0.76
    Pg
    -0.66
    bp
    -0.64
    cler
    -0.64
     Bounce
    -0.64
    uay
    -0.63
    way
    -0.62
     Louie
    -0.62
    WAYS
    -0.62
    POSITIVE LOGITS
    è¦
    0.73
     happened
    0.66
     programmed
    0.63
     wrong
    0.63
    irements
    0.62
     thrust
    0.62
    isites
    0.62
    ãĤ¯
    0.62
     scenario
    0.61
     guiActiveUn
    0.61
    Activations Density 0.106%

    No Known Activations