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. 0-RES-JB
    6. 21787
    Prev
    Next
    INDEX
    Explanations

    numerical values followed by the symbol '%' or special terms like GDP or 'votes'

    oai_token-act-pair · gpt-3.5-turbo

    numerical data or statistics related to quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anas
    -0.66
     yours
    -0.63
     cover
    -0.62
     theirs
    -0.61
     boarding
    -0.60
     planet
    -0.60
     Paula
    -0.60
     booking
    -0.59
     vacancy
    -0.59
     snow
    -0.58
    POSITIVE LOGITS
    32
    3.38
    64
    2.32
    31
    2.14
    33
    2.08
    34
    2.08
    16
    2.00
    42
    1.99
    36
    1.92
    38
    1.90
    35
    1.88
    Activations Density 0.024%

    No Known Activations