Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 19286
    Prev
    Next
    INDEX
    Explanations

    names or entities with the last name "Est"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Est" which likely refers to estimates or statistical measures

    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
    FACE
    -0.87
     Haram
    -0.73
    Pear
    -0.71
    powder
    -0.68
     revolving
    -0.68
    face
    -0.67
    dash
    -0.65
    spot
    -0.65
    hands
    -0.65
    kers
    -0.65
    POSITIVE LOGITS
    ablish
    1.27
    ablished
    1.22
     Est
    1.13
    imate
    1.06
     Lauder
    1.03
    Est
    1.00
     unden
    0.96
    acion
    0.95
    uary
    0.92
     corrid
    0.87
    Activations Density 0.009%

    No Known Activations