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. 0-RES-JB
    6. 3678
    Prev
    Next
    INDEX
    Explanations

    keywords related to enhancement or improvement

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with improvement or augmentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Carly
    -0.78
     Empty
    -0.72
     Methodist
    -0.72
    zl
    -0.71
     Dru
    -0.70
     Monthly
    -0.70
     Socialist
    -0.69
     Numbers
    -0.67
     Marxist
    -0.66
     Alphabet
    -0.66
    POSITIVE LOGITS
     enhanced
    2.80
     enhancement
    2.71
     enhance
    2.56
     enhancing
    2.56
     enhancements
    2.30
     enhances
    2.17
    enh
    2.03
    Enhanced
    1.91
    Enh
    1.86
     augment
    1.86
    Activations Density 0.020%

    No Known Activations