© 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. 20344
    Prev
    Next
    INDEX
    Explanations

    mentions of a person named "Jeh" or "Jeho" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Je" across various contexts

    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
    ancial
    -0.77
    IUM
    -0.74
    raviolet
    -0.73
    ãĥ¼ãĥĨ
    -0.72
    姫
    -0.71
    imately
    -0.70
     Anthem
    -0.69
    ificant
    -0.66
     rooting
    -0.65
    IFIED
    -0.64
    POSITIVE LOGITS
    opard
    1.25
    zeb
    1.05
    hovah
    0.96
    anty
    0.92
    ans
    0.91
    apons
    0.90
     Je
    0.89
    hn
    0.89
    zza
    0.88
    pee
    0.88
    Activations Density 0.006%

    No Known Activations