© 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. 6-RES-JB
    11. 2982
    Prev
    Next
    INDEX
    Explanations

    mathematical or numerical expressions with special characters

    oai_token-act-pair · gpt-3.5-turbo

    symbols or characters associated with numerical data or special formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anium
    -0.76
     Grimes
    -0.71
    iger
    -0.69
    essee
    -0.68
    owicz
    -0.68
    itzer
    -0.67
     Reloaded
    -0.65
     Lauder
    -0.65
    xton
    -0.64
    NER
    -0.63
    POSITIVE LOGITS
    /-
    1.25
    -+
    1.07
    /+
    0.94
    raid
    0.83
    Priv
    0.79
    chlor
    0.78
    ssh
    0.77
    -+-+-+-+
    0.76
    events
    0.76
    --+
    0.76
    Activations Density 0.019%

    No Known Activations