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. 22183
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "for every" associated with a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "for every [number]" used 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
    Ü
    -0.83
    por
    -0.76
    ãĤ¦ãĤ¹
    -0.75
    fried
    -0.73
    psc
    -0.73
    Jer
    -0.72
    banks
    -0.70
    fw
    -0.67
    hist
    -0.66
    glers
    -0.66
    POSITIVE LOGITS
     conceivable
    0.80
     dollar
    0.77
     successive
    0.74
    uana
    0.72
    THING
    0.70
    olar
    0.70
    missive
    0.70
     sake
    0.68
     succeeding
    0.68
     hour
    0.68
    Activations Density 0.043%

    No Known Activations