© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14734
    Prev
    Next
    INDEX
    Explanations

    names, specifically focusing on individuals named Johannes and Kath

    oai_token-act-pair · gpt-3.5-turbo

    the name "Johannes" and variations of it alongside names similar to "Kath" and "Leigh"

    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
    senal
    -0.88
    edience
    -0.82
    xual
    -0.79
    aneous
    -0.78
    ãĤ¨ãĥ«
    -0.78
    ahime
    -0.74
    selage
    -0.74
    illus
    -0.72
    cles
    -0.69
    lda
    -0.69
    POSITIVE LOGITS
     Johannes
    0.86
    Thor
    0.85
    mand
    0.79
    gow
    0.77
    oping
    0.73
    borg
    0.73
    bos
    0.72
    sten
    0.71
     Thor
    0.71
     Gunn
    0.70
    Activations Density 0.019%

    No Known Activations