© 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. 11-RES-JB
    11. 22437
    Prev
    Next
    INDEX
    Explanations

    phrases related to a series or sequence of events

    oai_token-act-pair · gpt-3.5-turbo

    references to ongoing series or sequences of events

    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
    nces
    -0.75
    enance
    -0.70
    wered
    -0.69
    anced
    -0.69
    intendent
    -0.68
    arten
    -0.68
    ofer
    -0.67
    ances
    -0.66
    agents
    -0.65
    facts
    -0.65
    POSITIVE LOGITS
     broader
    1.06
     larger
    1.03
     trilogy
    1.00
     longstanding
    0.98
     wider
    0.97
     lengthy
    0.97
     long
    0.96
     protracted
    0.94
     continuum
    0.93
     trend
    0.91
    Activations Density 0.132%

    No Known Activations