© 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. 1-RES-JB
    11. 3856
    Prev
    Next
    INDEX
    Explanations

    references to proper names and businesses

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "survey"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lapse
    -0.76
     supplementary
    -0.71
    phabet
    -0.69
     simultaneous
    -0.67
     immersion
    -0.66
     vigilance
    -0.64
     chopping
    -0.64
     retention
    -0.63
    Downloadha
    -0.63
     duplication
    -0.62
    POSITIVE LOGITS
    vey
    1.21
    ards
    1.06
    bugs
    0.85
    rand
    0.83
    rod
    0.82
    aire
    0.75
    gaard
    0.75
    age
    0.73
    tro
    0.73
    enegger
    0.72
    Activations Density 0.007%

    No Known Activations