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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 10-RES-JB
    6. 16898
    Prev
    Next
    INDEX
    Explanations

    dates and events from various years

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods, indicating the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tack
    -0.83
     allowable
    -0.80
     distribut
    -0.79
    usable
    -0.79
     pouch
    -0.76
     inconsist
    -0.76
     affili
    -0.76
     propensity
    -0.75
     readily
    -0.75
     nons
    -0.74
    POSITIVE LOGITS
     Congratulations
    1.29
     Thousands
    1.28
     Hundreds
    1.26
     Yesterday
    1.26
     Ahead
    1.20
     Dozens
    1.20
     Millions
    1.18
     Everyone
    1.17
     Whilst
    1.17
     Tonight
    1.14
    Activations Density 0.477%

    No Known Activations