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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 10668
    Prev
    Next
    INDEX
    Explanations

    References to large sums of money in the Indian numbering system

    oai_token-act-pair · gpt-3.5-turbo

    mentions of monetary values, particularly in the form of "crore" and "lakh."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    choes
    -0.72
    swick
    -0.70
    ALT
    -0.68
    aeper
    -0.68
    sonian
    -0.67
    ©¶æ
    -0.67
    furt
    -0.66
    irrel
    -0.64
    cknowled
    -0.64
    cers
    -0.62
    POSITIVE LOGITS
     crore
    1.00
     hectares
    0.90
     tonnes
    0.83
    votes
    0.78
     ru
    0.74
    +.
    0.74
     litres
    0.73
     dollars
    0.72
     acres
    0.71
    Reply
    0.70
    Activations Density 0.015%

    No Known Activations