© 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. 445
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a person or entity performing certain actions or exhibiting specific characteristics

    oai_token-act-pair · gpt-3.5-turbo
    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
     Header
    -0.51
     LM
    -0.49
     Mile
    -0.49
     Participation
    -0.48
     Gateway
    -0.48
     Millennium
    -0.47
     Measure
    -0.47
     Front
    -0.47
     Impact
    -0.46
     Dominion
    -0.46
    POSITIVE LOGITS
    zbollah
    1.21
    resy
    1.14
    aped
    1.03
    uristic
    1.01
    reditary
    0.98
    ctic
    0.94
    'll
    0.93
    'd
    0.93
    ading
    0.92
    avier
    0.92
    Activations Density 0.199%

    No Known Activations