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. 7-RES-JB
    6. 16981
    Prev
    Next
    INDEX
    Explanations

    words/phrases containing the characters 'ľ' or 'uns'

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the symbol 'ľ' and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     levers
    -0.72
     Zombies
    -0.72
     strips
    -0.71
     climbers
    -0.70
     apes
    -0.70
     rabbits
    -0.69
     pleasures
    -0.67
     ropes
    -0.66
     Pets
    -0.66
     participants
    -0.65
    POSITIVE LOGITS
    vernment
    1.06
    uthor
    1.02
    20439
    0.89
    payer
    0.87
    cffffcc
    0.86
    early
    0.84
    olitical
    0.84
    ishable
    0.83
    ï¸ı
    0.83
    fter
    0.81
    Activations Density 0.054%

    No Known Activations