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. 6-RES-JB
    6. 1376
    Prev
    Next
    INDEX
    Explanations

    dates written in the format of day, month, and year

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically periods and others in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     withd
    -0.85
     undermin
    -0.77
     recall
    -0.76
     chained
    -0.72
     recalled
    -0.70
     interrupted
    -0.68
     poisoning
    -0.68
     sustainability
    -0.67
     harassed
    -0.66
     independ
    -0.66
    POSITIVE LOGITS
     [+
    1.25
    jpg
    1.04
    5
    0.91
    05
    0.90
    gif
    0.89
    0
    0.87
    06
    0.86
    jar
    0.84
    txt
    0.83
    09
    0.82
    Activations Density 0.121%

    No Known Activations