© 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. 0-RES-JB
    11. 12988
    Prev
    Next
    INDEX
    Explanations

    dates

    oai_token-act-pair · gpt-3.5-turbo

    the date "29."

    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
    •Embedding Space Digit Features

    No Comments

    Negative Logits
     lob
    -0.72
    channelAvailability
    -0.68
    pox
    -0.66
    acus
    -0.64
    appa
    -0.64
    ota
    -0.64
    Ton
    -0.60
     antagon
    -0.60
    LOD
    -0.60
    ton
    -0.59
    POSITIVE LOGITS
     29
    2.75
     59
    1.93
     31
    1.91
     39
    1.89
     27
    1.85
    29
    1.78
     28
    1.78
     26
    1.76
     23
    1.72
     34
    1.71
    Activations Density 0.032%

    No Known Activations