© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 23319
    Prev
    Next
    INDEX
    Explanations

    financial and tax-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to specific numeric codes or identifiers related to financial and nonprofit sectors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tortured
    -0.66
    athering
    -0.65
    analysis
    -0.64
     Inquisition
    -0.64
    riel
    -0.63
     clen
    -0.62
     Inquis
    -0.59
    alone
    -0.58
     Enlightenment
    -0.58
     devils
    -0.58
    POSITIVE LOGITS
    \\\\\\\\
    0.81
    ħĭ
    0.81
    sylv
    0.77
    halla
    0.77
    yll
    0.75
     401
    0.75
    nance
    0.73
    reprene
    0.72
    uary
    0.72
    )</
    0.71
    Activations Density 0.014%

    No Known Activations