© 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. 2187
    Prev
    Next
    INDEX
    Explanations

    specific mentions of employees in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to employees in various contexts

    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
    avers
    -1.11
    poons
    -1.09
    hip
    -1.09
    ervatives
    -1.06
    uits
    -1.02
    cale
    -1.01
    aurus
    -0.99
    itters
    -0.98
    heet
    -0.98
    everal
    -0.97
    POSITIVE LOGITS
    holder
    0.80
     witness
    0.79
    OSP
    0.73
    stown
    0.72
    ATH
    0.69
     pilot
    0.69
    lier
    0.66
    cer
    0.64
    gha
    0.64
    NAME
    0.63
    Activations Density 0.045%

    No Known Activations