© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 19843
    Prev
    Next
    INDEX
    Explanations

    numerical stat lines in sports contexts

    oai_token-act-pair · gpt-3.5-turbo

    sequences that include numbers separated by slashes or periods

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

    No Comments

    Negative Logits
     Sylv
    -0.78
     Samar
    -0.71
     Constantin
    -0.71
     directors
    -0.66
     Survivors
    -0.66
     Forgotten
    -0.66
     Flav
    -0.65
     Shant
    -0.64
     Orn
    -0.64
     Hills
    -0.63
    POSITIVE LOGITS
    /.
    0.92
    adish
    0.86
    icago
    0.81
    -.
    0.78
     (.
    0.75
    wordpress
    0.75
     cubic
    0.75
    etc
    0.74
    Pg
    0.74
    PsyNetMessage
    0.73
    Activations Density 0.008%

    No Known Activations