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. 8-RES-JB
    6. 14655
    Prev
    Next
    INDEX
    Explanations

    URL parameters or tracking codes in website links

    oai_token-act-pair · gpt-3.5-turbo

    technical parameters and codes often used in data or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     counselors
    -0.64
     repercussions
    -0.63
     penalties
    -0.62
     ambassadors
    -0.61
    obos
    -0.60
     Armageddon
    -0.60
     temperament
    -0.59
     surrogate
    -0.59
     reass
    -0.58
     Turing
    -0.58
    POSITIVE LOGITS
    &
    0.99
    govtrack
    0.86
    album
    0.84
    rss
    0.84
    detail
    0.82
    sr
    0.81
    article
    0.79
    true
    0.77
    utf
    0.76
    wordpress
    0.75
    Activations Density 0.032%

    No Known Activations