© 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. 10-RES-JB
    11. 20556
    Prev
    Next
    INDEX
    Explanations

    references to the pseudonym "Satoshi"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Sat" or "sat" and related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    naire
    -0.86
    theless
    -0.73
    lessly
    -0.68
    GBT
    -0.63
     forthcoming
    -0.63
     symmetry
    -0.60
    CE
    -0.60
    taining
    -0.58
    mental
    -0.56
     accuracy
    -0.56
    POSITIVE LOGITS
    chel
    1.24
    ivas
    1.21
    iva
    1.21
    chell
    1.19
    oshi
    1.18
    anic
    1.18
    urn
    1.16
    iated
    1.11
    rina
    1.08
    iety
    1.07
    Activations Density 0.026%

    No Known Activations