© 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. 10-RES-JB
    11. 8313
    Prev
    Next
    INDEX
    Explanations

    references to specific actions or commands occurring in parentheses

    oai_token-act-pair · gpt-3.5-turbo

    the presence of parentheses

    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
     wildlife
    -0.78
     pale
    -0.74
     rang
    -0.74
     Academy
    -0.73
     heavily
    -0.72
     Thrones
    -0.71
     consolation
    -0.71
     star
    -0.71
     firmly
    -0.71
     dangerously
    -0.70
    POSITIVE LOGITS
    such
    1.86
    usually
    1.84
    typically
    1.80
    either
    1.73
    see
    1.71
    unless
    1.71
    often
    1.66
    although
    1.65
    including
    1.65
    whether
    1.64
    Activations Density 0.124%

    No Known Activations