© 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. 7-RES-JB
    11. 1527
    Prev
    Next
    INDEX
    Explanations

    phrases related to professional positions or affiliations

    oai_token-act-pair · gpt-3.5-turbo

    punctuated phrases indicating roles, positions, or statuses in a professional context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erence
    -0.76
    itals
    -0.75
     deficit
    -0.71
    estinal
    -0.70
    isy
    -0.69
     disadvantage
    -0.68
    iculty
    -0.67
    igl
    -0.67
     subst
    -0.66
    ipeg
    -0.65
    POSITIVE LOGITS
     LLC
    0.99
     Inc
    0.93
     Ltd
    0.84
     aka
    0.81
     whereby
    0.77
     Kinnikuman
    0.76
    Guard
    0.73
     whence
    0.71
     Calif
    0.70
     Ore
    0.70
    Activations Density 0.356%

    No Known Activations