© 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. 7764
    Prev
    Next
    INDEX
    Explanations

    phrases or clauses indicating an event or information coming to light

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the verb "come" followed by a preposition

    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
    vich
    -0.68
    croft
    -0.62
    ics
    -0.60
    cius
    -0.59
     waived
    -0.59
    sle
    -0.59
    yss
    -0.58
    sand
    -0.58
    resy
    -0.58
    º
    -0.58
    POSITIVE LOGITS
     fruition
    1.27
     pass
    0.93
     prominence
    0.93
     haunt
    0.93
     grips
    0.92
     light
    0.91
     blows
    0.90
     mind
    0.89
     define
    0.87
     dominate
    0.86
    Activations Density 0.042%

    No Known Activations