© 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. 9-RES-JB
    11. 13922
    Prev
    Next
    INDEX
    Explanations

    phrases related to increasing quantities or levels

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aiden
    -0.67
     Traff
    -0.63
    digy
    -0.62
    è£ħ
    -0.59
    leanor
    -0.57
    ĨĴ
    -0.57
    icho
    -0.57
    hack
    -0.56
    igslist
    -0.55
     robber
    -0.55
    POSITIVE LOGITS
    ween
    0.75
    rogen
    0.70
     clearer
    0.70
    itional
    0.69
     varied
    0.69
     better
    0.68
    rogens
    0.67
    impro
    0.67
    ificantly
    0.67
     faster
    0.67
    Activations Density 0.046%

    No Known Activations