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. 10-RES-JB
    6. 11702
    Prev
    Next
    INDEX
    Explanations

    terms related to an increasing quantity or degree

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "more."

    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
    xtap
    -0.90
    bat
    -0.76
    emet
    -0.76
    ername
    -0.75
    wered
    -0.74
    ader
    -0.71
    atan
    -0.70
    numbered
    -0.68
    ĺħ
    -0.68
    chest
    -0.67
    POSITIVE LOGITS
     than
    1.14
     importantly
    1.00
     stringent
    0.98
     frequent
    0.93
     emphasis
    0.92
     affluent
    0.92
     sophisticated
    0.88
     people
    0.86
     efficient
    0.83
     opportunities
    0.82
    Activations Density 0.126%

    No Known Activations