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. 2-RES-JB
    6. 2164
    Prev
    Next
    INDEX
    Explanations

    tokens related to blockchain and cryptocurrency

    oai_token-act-pair · gpt-3.5-turbo

    references to tokens in various contexts and usages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ichita
    -0.74
     Schr
    -0.73
    riend
    -0.71
     Curt
    -0.69
     Cause
    -0.68
     Rove
    -0.68
    Friend
    -0.67
    ECD
    -0.66
     Cook
    -0.66
    friend
    -0.64
    POSITIVE LOGITS
     tokens
    1.26
     token
    1.22
     holders
    0.95
    holders
    0.91
    token
    0.89
     Tokens
    0.87
     guiActiveUn
    0.85
     Token
    0.85
    opol
    0.82
    itory
    0.82
    Activations Density 0.007%

    No Known Activations