© 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. 3308
    Prev
    Next
    INDEX
    Explanations

    personal reflections and anecdotes

    oai_token-act-pair · gpt-3.5-turbo
    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
    ij士
    -0.83
     Vote
    -0.79
     Warranty
    -0.74
     Verify
    -0.73
     REPORT
    -0.73
    Secure
    -0.72
    Residents
    -0.71
    Vote
    -0.70
     duly
    -0.70
     Officials
    -0.70
    POSITIVE LOGITS
     autobi
    1.19
    laughs
    1.13
     ['
    1.05
     lyr
    1.02
     genres
    1.02
     fuckin
    0.95
     influences
    0.93
     autobiography
    0.92
     spirituality
    0.92
     upbringing
    0.92
    Activations Density 0.688%

    No Known Activations