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. 898
    Prev
    Next
    INDEX
    Explanations

    years in the format "XXXX" where XXXX is the year

    oai_token-act-pair · gpt-3.5-turbo

    the repeated occurrence of the number 54 in various contexts

    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
     wine
    -0.71
    rast
    -0.67
     veget
    -0.66
    irit
    -0.63
    nect
    -0.63
     neut
    -0.63
     gray
    -0.63
     VAT
    -0.62
    rington
    -0.61
     Spaces
    -0.61
    POSITIVE LOGITS
    54
    2.20
     54
    1.77
    74
    1.61
    94
    1.53
     1954
    1.40
    254
    1.38
    84
    1.37
    34
    1.34
    954
    1.33
     74
    1.32
    Activations Density 0.061%

    No Known Activations