© 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. 10-RES-JB
    11. 8009
    Prev
    Next
    INDEX
    Explanations

    the conjunction "which is" patterns

    oai_token-act-pair · gpt-3.5-turbo

    statements indicating definitions or explanations

    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
    otte
    -0.86
    actory
    -0.76
    rongh
    -0.73
    ievers
    -0.72
    nikov
    -0.70
    arella
    -0.67
    icators
    -0.67
    oided
    -0.66
    Numbers
    -0.65
    igraph
    -0.63
    POSITIVE LOGITS
     why
    1.49
     understandable
    1.13
     admittedly
    1.11
     ironic
    1.05
     presumably
    1.05
     basically
    1.02
    why
    1.00
     supposed
    0.94
     WHY
    0.93
     exactly
    0.93
    Activations Density 0.118%

    No Known Activations