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. 3-RES-JB
    6. 22149
    Prev
    Next
    INDEX
    Explanations

    references to a specific sports team - the Mets

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the New York Mets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ħĭ
    -0.75
    judicial
    -0.71
    ommel
    -0.70
    fully
    -0.69
    SPONSORED
    -0.69
    lying
    -0.67
    gging
    -0.63
    pressed
    -0.62
     hemisphere
    -0.61
     attribution
    -0.61
    POSITIVE LOGITS
    terson
    0.78
    peed
    0.77
     Slug
    0.76
     Mets
    0.74
    erv
    0.69
    rix
    0.68
    arella
    0.68
    worth
    0.67
     infield
    0.67
     Stadium
    0.66
    Activations Density 0.005%

    No Known Activations