Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 22950
    Prev
    Next
    INDEX
    Explanations

    words related to cryptocurrency

    oai_token-act-pair · gpt-3.5-turbo

    mentions of cryptocurrency and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Loving
    -0.76
    NING
    -0.72
     Phelps
    -0.68
     Yemeni
    -0.66
     Hanson
    -0.63
    witz
    -0.63
     Ng
    -0.63
     ALS
    -0.62
     ABE
    -0.61
    UGH
    -0.61
    POSITIVE LOGITS
    ozo
    1.33
    ographically
    1.30
    ographers
    1.11
    onyms
    1.08
    analysis
    1.07
    ographer
    1.03
    ogram
    1.03
    ographic
    1.03
    ograms
    1.02
    opsy
    1.02
    Activations Density 0.014%

    No Known Activations