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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 17543
    Prev
    Next
    INDEX
    Explanations

    names of people or entities ending in 'worth'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "worth" and its variations in different contexts

    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
     deaf
    -0.67
     jerk
    -0.63
     disturbing
    -0.62
     heter
    -0.61
     heartbeat
    -0.61
     Wikileaks
    -0.60
     Alexa
    -0.60
     cynical
    -0.59
    PDATE
    -0.58
     awoken
    -0.57
    POSITIVE LOGITS
    worth
    1.26
    sburg
    1.16
    borough
    0.98
    doms
    0.94
    sworth
    0.93
    sung
    0.89
    pole
    0.88
    onge
    0.87
    bye
    0.85
    halla
    0.83
    Activations Density 0.009%

    No Known Activations