© 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. 7-RES-JB
    11. 3049
    Prev
    Next
    INDEX
    Explanations

    mentions of small entities or objects

    oai_token-act-pair · gpt-3.5-turbo

    references to small-scale entities or businesses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     largeDownload
    -0.72
     Rousse
    -0.71
    ILLE
    -0.65
     Machina
    -0.62
    ilee
    -0.62
    undrum
    -0.61
    ophen
    -0.61
     showc
    -0.61
    èĥ
    -0.61
    rigan
    -0.60
    POSITIVE LOGITS
    pox
    1.18
     intestine
    0.93
     increments
    0.92
     sized
    0.87
    folk
    0.84
     fry
    0.83
     (<
    0.81
    hearted
    0.81
     batches
    0.80
    scale
    0.77
    Activations Density 0.044%

    No Known Activations