© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 5582
    Prev
    Next
    INDEX
    Explanations

    pessimistic or critical statements within parentheses

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and symbols, particularly parentheses and quotation marks

    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
    ande
    -0.80
    bek
    -0.79
    ometimes
    -0.77
    ãħĭãħĭ
    -0.74
    ãħĭ
    -0.73
    wright
    -0.71
    pecially
    -0.70
    apult
    -0.69
    jen
    -0.68
    ervative
    -0.68
    POSITIVE LOGITS
     versions
    0.90
     version
    0.77
     portions
    0.68
     editions
    0.68
     counterparts
    0.67
     relationships
    0.66
     ones
    0.65
     approach
    0.65
     reproduction
    0.64
     marriages
    0.64
    Activations Density 0.097%

    No Known Activations