© 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. 11-RES-JB
    11. 9848
    Prev
    Next
    INDEX
    Explanations

    commands or statements indicating a need for action or warning

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey advice or warnings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umerable
    -0.80
    ruciating
    -0.67
    binding
    -0.63
    quickShipAvailable
    -0.60
     Via
    -0.60
    ItemImage
    -0.59
    Ĭ±
    -0.57
    regor
    -0.56
    mediated
    -0.56
    accessible
    -0.55
    POSITIVE LOGITS
     hurry
    1.21
     beware
    1.03
     buckle
    0.98
     watch
    0.92
     admit
    0.92
     prepare
    0.91
     celebrate
    0.91
     believe
    0.89
     invest
    0.89
     hope
    0.89
    Activations Density 0.079%

    No Known Activations