© 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 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. 3-RES-JB
    11. 24423
    Prev
    Next
    INDEX
    Explanations

    terms related to probability theory

    oai_token-act-pair · gpt-3.5-turbo

    terms related to probability and statistical analysis

    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
    artney
    -0.96
    rine
    -0.92
    este
    -0.87
    amped
    -0.83
    ebus
    -0.83
    ined
    -0.82
    agra
    -0.80
    ines
    -0.78
    inas
    -0.77
    ilver
    -0.76
    POSITIVE LOGITS
     probability
    1.03
    llor
    0.93
     probabilities
    0.92
    chance
    0.79
     unbeliev
    0.75
    osate
    0.73
    abl
    0.71
     chance
    0.71
     density
    0.70
     inference
    0.69
    Activations Density 0.011%

    No Known Activations