© 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. 4058
    Prev
    Next
    INDEX
    Explanations

    combinations of items or factors

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating various types of combinations

    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
    yers
    -0.85
    artisan
    -0.73
    ternity
    -0.70
    criptions
    -0.70
    gor
    -0.70
    Merit
    -0.69
    selves
    -0.69
    si
    -0.68
    ond
    -0.68
    iak
    -0.68
    POSITIVE LOGITS
     combinations
    0.79
     combines
    0.73
     thereof
    0.72
     seamlessly
    0.70
     combination
    0.70
    ively
    0.69
     lengths
    0.68
     headaches
    0.68
    ãĤ¤ãĥĪ
    0.67
     outputs
    0.64
    Activations Density 0.020%

    No Known Activations