© 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. 13647
    Prev
    Next
    INDEX
    Explanations

    mentions of authoritative or governmental figures and actions

    oai_token-act-pair · gpt-3.5-turbo

    discussions around decision-making and accountability in public contexts

    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
    /
    -0.66
    Newsletter
    -0.63
    taboola
    -0.63
     respectively
    -0.58
     Byz
    -0.56
    ezvous
    -0.56
    igon
    -0.56
     resid
    -0.55
    %);
    -0.55
     Trog
    -0.55
    POSITIVE LOGITS
    ?!"
    0.96
     such
    0.96
    !?"
    0.88
     blatantly
    0.86
     suddenly
    0.85
    ?!
    0.84
     mere
    0.84
    !?
    0.83
     solely
    0.80
     someone
    0.79
    Activations Density 0.899%

    No Known Activations