© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 17848
    Prev
    Next
    INDEX
    Explanations

    numerical comparisons or quantities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "more" and its variations to indicate an increase or addition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tracker
    -0.77
    otto
    -0.70
     Presence
    -0.68
     Attribution
    -0.68
     Handling
    -0.66
     Religion
    -0.66
     foresee
    -0.63
     estimating
    -0.62
    ENCE
    -0.61
    brance
    -0.61
    POSITIVE LOGITS
    esome
    0.80
    ricular
    0.78
     entries
    0.75
     reasons
    0.74
     activ
    0.73
    milo
    0.72
     installments
    0.70
    things
    0.69
     snaps
    0.69
    stro
    0.68
    Activations Density 0.110%

    No Known Activations