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. 21999
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or possibility

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express potentiality or conditionality

    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
    eye
    -0.70
    resso
    -0.69
     Bene
    -0.65
    athing
    -0.64
     Dear
    -0.64
    ament
    -0.63
    raint
    -0.62
    bern
    -0.62
     Columb
    -0.62
    arthed
    -0.61
    POSITIVE LOGITS
     require
    1.02
     escalate
    0.99
     delay
    0.99
     vary
    0.98
     postpone
    0.98
     shorten
    0.97
     exacerbate
    0.96
     complicate
    0.94
     modify
    0.94
     involve
    0.93
    Activations Density 0.188%

    No Known Activations