© 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. 11-RES-JB
    11. 22528
    Prev
    Next
    INDEX
    Explanations

    prices and numerical values in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    numerical values associated with measurements or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     65
    -0.69
     75
    -0.68
     70
    -0.67
     60
    -0.67
     72
    -0.66
     Mechdragon
    -0.65
     80
    -0.64
     Pigs
    -0.63
     bots
    -0.62
     stout
    -0.62
    POSITIVE LOGITS
    08
    1.49
    04
    1.47
    06
    1.46
    05
    1.45
    09
    1.45
    075
    1.45
    07
    1.44
    008
    1.44
    019
    1.43
    024
    1.43
    Activations Density 0.084%

    No Known Activations