© 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. 22155
    Prev
    Next
    INDEX
    Explanations

    proper nouns or terms related to specific locations, entities, or people

    oai_token-act-pair · gpt-3.5-turbo

    words that include the substring "oval."

    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
     Dying
    -0.74
    illing
    -0.69
    igmatic
    -0.69
     Fargo
    -0.66
     Revelations
    -0.66
     Codex
    -0.60
    ivals
    -0.60
     Humanity
    -0.59
     Nightmares
    -0.59
    wb
    -0.59
    POSITIVE LOGITS
    oval
    0.97
    mage
    0.84
    ilaterally
    0.82
    ogue
    0.80
    itri
    0.76
    anie
    0.74
    ipop
    0.73
    ensis
    0.73
    aries
    0.73
    istry
    0.71
    Activations Density 0.019%

    No Known Activations