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. 1-RES-JB
    6. 8303
    Prev
    Next
    INDEX
    Explanations

    mentions of Bengal or Bengal-related content

    oai_token-act-pair · gpt-3.5-turbo

    references to Bengal and Bengal-related entities, particularly tigers and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ö¼
    -0.92
    mble
    -0.92
    ipple
    -0.76
    ettings
    -0.75
    POS
    -0.68
    utherford
    -0.68
    endez
    -0.68
    yll
    -0.68
    eting
    -0.68
    ynt
    -0.67
    POSITIVE LOGITS
     Bengal
    1.23
    uru
    1.09
     tigers
    1.01
     Nadu
    0.97
    ataka
    0.89
     tiger
    0.86
    icum
    0.86
     Pradesh
    0.85
     beetles
    0.81
    ²¾
    0.79
    Activations Density 0.007%

    No Known Activations