© 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. 6-RES-JB
    11. 12054
    Prev
    Next
    INDEX
    Explanations

    words that are related to a specific book, possibly related to hidden secrets or details within the book

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ss" within words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ£
    -0.72
    TPP
    -0.68
    paralle
    -0.66
    ts
    -0.62
     Petraeus
    -0.62
    wealth
    -0.61
    few
    -0.61
    tained
    -0.61
     Kut
    -0.60
    scene
    -0.60
    POSITIVE LOGITS
    ault
    1.11
    alid
    1.04
    ession
    1.03
    ystem
    1.02
    creen
    0.98
    ometimes
    0.97
    essions
    0.95
    andra
    0.95
    alon
    0.94
    arah
    0.94
    Activations Density 0.016%

    No Known Activations