© 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. 6781
    Prev
    Next
    INDEX
    Explanations

    references to the University of California (UC) system

    oai_token-act-pair · gpt-3.5-turbo

    references to the University of California system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Samson
    -0.77
     lashed
    -0.76
     lash
    -0.74
    `
    -0.72
     Malk
    -0.72
     dips
    -0.69
    sein
    -0.68
     lashes
    -0.67
     Kinect
    -0.67
    ///
    -0.66
    POSITIVE LOGITS
     UC
    3.79
    UC
    2.40
     UCS
    2.24
     UCLA
    1.77
     UW
    1.66
     UNC
    1.57
     USC
    1.52
     Berkeley
    1.51
     UT
    1.42
     NYU
    1.36
    Activations Density 0.008%

    No Known Activations