© 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. 9-RES-JB
    11. 6876
    Prev
    Next
    INDEX
    Explanations

    instances of the word "there" indicating the presence of a subsequent action or condition

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    making
    -0.65
    telling
    -0.62
    ONSORED
    -0.61
    makers
    -0.61
     HIM
    -0.55
     actionGroup
    -0.54
     Consent
    -0.54
    arding
    -0.53
    Explore
    -0.53
     ABV
    -0.52
    POSITIVE LOGITS
    abouts
    0.99
    zbollah
    0.94
    itia
    0.93
    apo
    0.88
     Comes
    0.80
    arity
    0.74
     was
    0.73
    ikh
    0.73
    ipl
    0.72
    ileaks
    0.70
    Activations Density 0.044%

    No Known Activations