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. 21477
    Prev
    Next
    INDEX
    Explanations

    addresses or mentions of addresses in texts

    oai_token-act-pair · gpt-3.5-turbo

    references to specific addresses

    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
    lime
    -0.76
    fps
    -0.75
    uj
    -0.74
    drm
    -0.73
    apt
    -0.69
    umbers
    -0.68
     Kirin
    -0.67
    imposed
    -0.65
    nature
    -0.65
    retty
    -0.64
    POSITIVE LOGITS
     addr
    0.91
    holder
    0.84
     Address
    0.83
     address
    0.80
    holders
    0.76
    chool
    0.74
     addresses
    0.70
    irect
    0.66
    onica
    0.66
    plate
    0.65
    Activations Density 0.029%

    No Known Activations