© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6878
    Prev
    Next
    INDEX
    Explanations

    situations involving decisions or actions

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to urgency and caution in decision-making contexts

    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
     ain
    -0.72
    cellaneous
    -0.63
    fortunately
    -0.62
    requires
    -0.62
     hilar
    -0.62
    iom
    -0.62
     fascinating
    -0.61
     ingenious
    -0.61
     surprisingly
    -0.60
     resides
    -0.59
    POSITIVE LOGITS
     anymore
    0.75
     ousted
    0.72
     Benghazi
    0.66
     Bannon
    0.64
     unaccompanied
    0.64
     Qatar
    0.63
    20439
    0.63
     dossier
    0.63
     Breitbart
    0.63
     Brexit
    0.63
    Activations Density 1.259%

    No Known Activations