© 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. 10680
    Prev
    Next
    INDEX
    Explanations

    words related to importance or necessity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to essential qualities or characteristics that are deemed necessary or valuable

    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
    rams
    -0.82
    atures
    -0.80
    ancies
    -0.76
     timelines
    -0.76
    poons
    -0.74
     stakes
    -0.72
    ensions
    -0.72
    rity
    -0.71
    ignt
    -0.70
     chambers
    -0.70
    POSITIVE LOGITS
     deterrent
    0.84
     reel
    0.81
     garn
    0.78
     awaits
    0.77
     punishable
    0.77
     unto
    0.73
    brainer
    0.73
    IER
    0.72
    ãĥĩãĤ£
    0.70
     awaited
    0.68
    Activations Density 0.296%

    No Known Activations