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. 11-RES-JB
    6. 8699
    Prev
    Next
    INDEX
    Explanations

    words related to rocks and geological formations

    oai_token-act-pair · gpt-3.5-turbo

    references to rocks and geological formations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ufact
    -0.74
    License
    -0.65
    oÄŁ
    -0.64
    uthor
    -0.63
     Nationwide
    -0.63
    Express
    -0.62
    ECA
    -0.61
     accredited
    -0.61
    ORTS
    -0.61
    iator
    -0.61
    POSITIVE LOGITS
     quar
    1.14
     formations
    1.10
     quarry
    1.09
     climbers
    0.93
     slab
    0.92
     bould
    0.92
    anguage
    0.89
    falls
    0.88
     formation
    0.87
     sculpture
    0.87
    Activations Density 0.045%

    No Known Activations