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. 3-RES-JB
    6. 19548
    Prev
    Next
    INDEX
    Explanations

    numbers or quantifications, particularly the word "thousands."

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "thousands of" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ħĭ
    -0.76
    ĸļ
    -0.71
    acea
    -0.71
    iquette
    -0.69
    soType
    -0.64
     Directive
    -0.64
    SourceFile
    -0.63
     fundament
    -0.63
    Render
    -0.61
    ļéĨĴ
    -0.61
    POSITIVE LOGITS
     kilometers
    0.85
     miles
    0.84
     dollars
    0.83
     acres
    0.81
     pounds
    0.79
     kilometres
    0.79
     thousands
    0.78
    pees
    0.71
     gallons
    0.71
     hectares
    0.70
    Activations Density 0.165%

    No Known Activations