© 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. 10-RES-JB
    11. 12865
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals

    oai_token-act-pair · gpt-3.5-turbo

    variations of the name "Darryl" and other similar names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cffff
    -0.70
     metaphor
    -0.66
     compromise
    -0.65
     tipping
    -0.62
     respons
    -0.61
     obstruction
    -0.60
     pen
    -0.60
    izoph
    -0.59
     amnesty
    -0.59
     exc
    -0.59
    POSITIVE LOGITS
    nda
    0.97
    tta
    0.88
    von
    0.88
    lene
    0.87
    lla
    0.86
    enne
    0.86
    xia
    0.85
    hea
    0.81
    ndra
    0.80
    ela
    0.80
    Activations Density 0.075%

    No Known Activations