© 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. 11-RES-JB
    11. 23313
    Prev
    Next
    INDEX
    Explanations

    numerical measurements and percentages

    oai_token-act-pair · gpt-3.5-turbo

    statistical data related to rates and percentages

    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
    illions
    -0.67
     untold
    -0.61
    catentry
    -0.60
    avascript
    -0.56
     array
    -0.55
    bris
    -0.55
     marching
    -0.55
     limitless
    -0.54
     expend
    -0.54
    ãĥīãĥ©
    -0.53
    POSITIVE LOGITS
    %.
    1.54
    %,
    1.49
    %;
    1.44
    %:
    1.19
    %).
    1.02
    %-
    0.96
     percent
    0.94
    %),
    0.91
    %
    0.88
     percentage
    0.84
    Activations Density 0.123%

    No Known Activations