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. 23850
    Prev
    Next
    INDEX
    Explanations

    nouns with more than four letters starting or ending with 'ir' or 'ar'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific words and phrases related to cosmic and astronomical themes

    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
     slee
    -0.67
    ngth
    -0.64
     tentacles
    -0.59
     SV
    -0.57
     Morty
    -0.56
     transpl
    -0.55
    ONSORED
    -0.55
     tight
    -0.55
     fed
    -0.55
     warr
    -0.55
    POSITIVE LOGITS
    ocally
    0.85
    aque
    0.85
    ilogy
    0.83
    que
    0.77
    quel
    0.75
    zees
    0.75
    mire
    0.75
    bush
    0.74
    zee
    0.74
    itely
    0.70
    Activations Density 0.061%

    No Known Activations