© 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. 0-RES-JB
    11. 16371
    Prev
    Next
    INDEX
    Explanations

    terms related to electronic technology

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     heal
    -0.78
     gor
    -0.77
     healed
    -0.73
     plat
    -0.73
     worsen
    -0.73
     rav
    -0.72
     haunt
    -0.71
    %%%%
    -0.70
     sag
    -0.67
     scapego
    -0.67
    POSITIVE LOGITS
     Electronic
    3.84
     Electronics
    1.60
    Elect
    1.56
     EFF
    1.44
     Computer
    1.40
     EA
    1.26
     Electrical
    1.23
     Digital
    1.19
     Interactive
    1.18
     Telecommunications
    1.18
    Activations Density 0.021%

    No Known Activations