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. 4-RES-JB
    6. 8422
    Prev
    Next
    INDEX
    Explanations

    phrases related to someone's upbringing or place they were brought up in

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "raise" and its variations, suggesting it is focused on themes of upbringing or nurturing

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

    No Comments

    Negative Logits
    icity
    -0.81
    ician
    -0.73
    entials
    -0.73
    pedia
    -0.70
    emp
    -0.68
    ian
    -0.67
    cas
    -0.66
    tical
    -0.63
    jamin
    -0.62
    ious
    -0.62
    POSITIVE LOGITS
    xual
    0.91
    raised
    0.89
     eyebrows
    0.83
     raised
    0.79
     chickens
    0.77
    raising
    0.72
     raising
    0.71
    byn
    0.70
    FontSize
    0.68
    heses
    0.67
    Activations Density 0.021%

    No Known Activations