© 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. 14914
    Prev
    Next
    INDEX
    Explanations

    sentences that emphasize speaking or expressing ideas in a direct or candid manner

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to candid communication and truth-telling

    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
    ģĸ
    -0.63
    hesda
    -0.62
     additions
    -0.61
    gerald
    -0.61
    TRY
    -0.60
    ucket
    -0.60
    irements
    -0.59
    ~~~~~~~~~~~~~~~~
    -0.59
    ãĥł
    -0.59
    Missing
    -0.58
    POSITIVE LOGITS
     aloud
    1.04
     louder
    0.99
     voic
    0.95
     tongues
    0.94
     loudly
    0.92
     language
    0.90
     talk
    0.90
     loud
    0.90
     dialect
    0.90
    voice
    0.86
    Activations Density 0.265%

    No Known Activations