© 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. 7-RES-JB
    11. 23772
    Prev
    Next
    INDEX
    Explanations

    the verb "is" within phrases

    oai_token-act-pair · gpt-3.5-turbo

    statements asserting the existence or importance of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    luaj
    -0.79
    sburg
    -0.72
     plates
    -0.69
    chev
    -0.66
    ngth
    -0.62
    bies
    -0.62
    fields
    -0.61
    izens
    -0.60
    assies
    -0.59
     joints
    -0.59
    POSITIVE LOGITS
     contrasted
    0.95
     especially
    0.86
     exacerbated
    0.85
     partly
    0.80
     understandable
    0.79
     particularly
    0.79
     essentially
    0.77
     unsur
    0.77
     analogous
    0.77
    quickShipAvailable
    0.75
    Activations Density 0.179%

    No Known Activations