© 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. 2-RES-JB
    11. 17677
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "isse" at varying relevance levels

    oai_token-act-pair · gpt-3.5-turbo

    references to connoisseurship and discussions about quality in various domains

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kev
    -0.64
     peril
    -0.62
     Defenders
    -0.61
    angering
    -0.59
    emonic
    -0.58
     Sixth
    -0.57
     parks
    -0.57
    healthy
    -0.56
     ILCS
    -0.56
    groups
    -0.56
    POSITIVE LOGITS
    isse
    1.05
    isen
    0.98
    udo
    0.93
    mination
    0.92
    lette
    0.91
    clair
    0.90
     horizont
    0.89
    zon
    0.88
    vier
    0.87
    zes
    0.84
    Activations Density 0.004%

    No Known Activations