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

    Neuronpedia

    Jacobian LensNEW
    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. 564
    Prev
    Next
    INDEX
    Explanations

    the word "sheer" indicating intensity or magnitude

    oai_token-act-pair · gpt-4-turbo

    the word "sheer" followed by an adjective or noun

    oai_token-act-pair · gpt-3.5-turbo

    the intensity or magnitude of a quality or quantity, particularly focusing on the word "sheer."

    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
    anwhile
    -0.87
    afort
    -0.79
    artments
    -0.74
    lict
    -0.74
    ublic
    -0.74
    ishops
    -0.71
    olar
    -0.71
    olen
    -0.70
    istant
    -0.69
    alian
    -0.68
    POSITIVE LOGITS
     sheer
    0.91
    tons
    0.82
     volume
    0.81
     quantities
    0.76
     plain
    0.73
     coincidence
    0.73
     quantity
    0.71
     amounts
    0.69
     numbers
    0.68
    ãĥ©ãĥ³
    0.67
    Activations Density 0.006%

    No Known Activations