Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 24447
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions associated with mental health or political terminology, especially the word "schism"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "sch" and variations of the term "convene" along with the related concept of secrecy or underlying issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uca
    -0.85
    roma
    -0.80
    Bell
    -0.77
     Lamp
    -0.75
    alez
    -0.73
    Choice
    -0.72
    reath
    -0.71
     Discount
    -0.71
    Winged
    -0.70
     Operator
    -0.70
    POSITIVE LOGITS
     sch
    2.29
     conven
    2.20
     unse
    1.65
     adjourn
    1.40
     arche
    1.37
     tra
    1.11
     colleg
    1.11
     lik
    1.10
     convened
    1.03
     scr
    1.00
    Activations Density 0.047%

    No Known Activations