© 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. 1-RES-JB
    11. 13116
    Prev
    Next
    INDEX
    Explanations

    references to specific financial and tax-related codes or regulations, such as "401k" and "501c"

    oai_token-act-pair · gpt-3.5-turbo

    references to retirement plans and financial codes

    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
     imposition
    -0.78
     tampering
    -0.78
     agitation
    -0.69
    oles
    -0.67
     Inquisition
    -0.66
     fixation
    -0.65
     Inqu
    -0.63
     Parliament
    -0.63
     intimidation
    -0.62
     repression
    -0.62
    POSITIVE LOGITS
    \\\\\\\\
    0.94
     401
    0.94
     501
    0.92
    BUG
    0.84
    ertodd
    0.80
    sylv
    0.80
    OHN
    0.80
    irie
    0.78
    ĨĴ
    0.77
    501
    0.77
    Activations Density 0.008%

    No Known Activations