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. 1-RES-JB
    6. 9216
    Prev
    Next
    INDEX
    Explanations

    keywords related to cryptocurrencies and medical conditions like clots

    oai_token-act-pair · gpt-3.5-turbo

    references to cryptocurrency and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     POLIT
    -0.83
     Roosevelt
    -0.72
    committee
    -0.69
    WHO
    -0.65
    ITY
    -0.64
    OURCE
    -0.62
     Slovakia
    -0.62
     WR
    -0.61
    iannopoulos
    -0.61
    \-
    -0.61
    POSITIVE LOGITS
    stals
    1.58
    Cry
    1.21
    sis
    1.19
    stall
    1.06
     Cry
    1.06
    pter
    1.00
    stal
    0.98
    gments
    0.82
    cry
    0.81
     Primal
    0.77
    Activations Density 0.008%

    No Known Activations