© 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. 24394
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "fire" in the context of various topics

    oai_token-act-pair · gpt-3.5-turbo

    references to the brand or product named "Pirelli."

    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
    ¬¼
    -0.72
     Mehran
    -0.70
    eston
    -0.69
    sylv
    -0.68
    aughed
    -0.67
    ĸļ
    -0.65
    iary
    -0.65
    onent
    -0.64
    izers
    -0.62
    atform
    -0.62
    POSITIVE LOGITS
    nces
    1.47
    lli
    1.33
    ttes
    1.12
    lla
    1.10
    llo
    1.03
    tta
    1.00
    nder
    0.98
    ndra
    0.95
    cki
    0.92
    lington
    0.91
    Activations Density 0.045%

    No Known Activations