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. 8651
    Prev
    Next
    INDEX
    Explanations

    mentions of the "FA Cup", which is a football competition

    oai_token-act-pair · gpt-3.5-turbo

    references to the FA (Football Association) Cup

    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
    tie
    -0.71
     Horton
    -0.70
    Trend
    -0.70
    come
    -0.67
    atchewan
    -0.66
    frames
    -0.63
    down
    -0.62
    andem
    -0.62
     Lizard
    -0.62
     Reson
    -0.62
    POSITIVE LOGITS
    FA
    0.99
    BIP
    0.87
    uthor
    0.87
    FF
    0.85
    ILS
    0.84
    VE
    0.84
    ctions
    0.84
    ruits
    0.83
    ULTS
    0.83
    ITH
    0.83
    Activations Density 0.008%

    No Known Activations