© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 6259
    Prev
    Next
    INDEX
    Explanations

    features related to computer code snippets or other structured data formats

    oai_token-act-pair · gpt-3.5-turbo

    references related to business and professional endeavors

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

    No Comments

    Negative Logits
     untreated
    -0.52
    azo
    -0.52
     peninsula
    -0.49
    oshenko
    -0.47
    acial
    -0.47
     disapp
    -0.46
     cavity
    -0.46
    inki
    -0.46
     unidentified
    -0.46
    poral
    -0.45
    POSITIVE LOGITS
     Camel
    0.68
    enment
    0.65
     Gleaming
    0.63
    ĨĴ
    0.61
    Magikarp
    0.56
     Stout
    0.56
     Classics
    0.55
    merce
    0.53
    Dou
    0.52
    Jess
    0.52
    Activations Density 2.214%

    No Known Activations