© 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. 4-RES-JB
    11. 16242
    Prev
    Next
    INDEX
    Explanations

    adjectives related to describing something as extreme or intense

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of being suitable or deserving

    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
    aptic
    -0.89
    spe
    -0.82
    href
    -0.80
    erva
    -0.79
    romy
    -0.78
    atto
    -0.78
    opsis
    -0.77
    involved
    -0.77
    hetamine
    -0.77
    ulet
    -0.76
    POSITIVE LOGITS
    itable
    0.82
     convergence
    0.73
     hazard
    0.71
     appendix
    0.71
     bye
    0.68
     Haram
    0.68
     contribution
    0.68
     Mae
    0.66
     cov
    0.66
     Clyde
    0.65
    Activations Density 0.028%

    No Known Activations