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. 6-RES-JB
    6. 9418
    Prev
    Next
    INDEX
    Explanations

    phrases related to percentages and ratios

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating percentages related to financial or economic data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hunt
    -0.66
    spir
    -0.65
    pedia
    -0.63
    æĦ
    -0.63
    anyahu
    -0.61
    mpeg
    -0.61
    named
    -0.60
    _>
    -0.59
    sort
    -0.59
    andal
    -0.58
    POSITIVE LOGITS
     GDP
    0.96
     GN
    0.71
     households
    0.68
    pees
    0.67
     respondents
    0.64
     earners
    0.64
     total
    0.63
    payers
    0.61
     Dollars
    0.61
     Clover
    0.61
    Activations Density 0.067%

    No Known Activations