© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-RES-JB
    11. 10435
    Prev
    Next
    INDEX
    Explanations

    references to screen resolutions

    oai_token-act-pair · gpt-3.5-turbo

    references to 4K and 5G technology specifications and features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    essor
    -0.61
     HUM
    -0.61
     nonexistent
    -0.60
    recated
    -0.59
     Lua
    -0.59
    ortunately
    -0.58
    raltar
    -0.58
    yll
    -0.58
     Rudolph
    -0.57
     Ridley
    -0.57
    POSITIVE LOGITS
     apiece
    1.04
    bps
    0.99
    reens
    0.78
    IU
    0.76
     volts
    0.76
    degree
    0.75
    GHz
    0.75
     acres
    0.75
     onwards
    0.73
    undred
    0.73
    Activations Density 0.407%

    No Known Activations