© 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. 6-RES-JB
    11. 17635
    Prev
    Next
    INDEX
    Explanations

    time measurements, particularly seconds

    oai_token-act-pair · gpt-3.5-turbo

    references to time measurements in seconds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inav
    -0.69
    irie
    -0.69
    hammer
    -0.68
    stra
    -0.67
    annis
    -0.65
    oret
    -0.61
    esan
    -0.61
    elf
    -0.60
    gat
    -0.60
    iHUD
    -0.60
    POSITIVE LOGITS
     elapsed
    1.22
    aneously
    0.88
     intervals
    0.84
    ngth
    0.82
     ago
    0.81
     apiece
    0.77
     increments
    0.73
     msec
    0.72
    glass
    0.72
     interval
    0.72
    Activations Density 0.023%

    No Known Activations