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. 11-RES-JB
    6. 19652
    Prev
    Next
    INDEX
    Explanations

    phrases related to treating or handling something or someone in a certain way

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "treat" and its variations in various contexts, particularly relating to treatment and care

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hire
    -0.67
    inx
    -0.66
    fix
    -0.65
    dt
    -0.64
    sign
    -0.64
    aer
    -0.64
    sky
    -0.59
    thal
    -0.58
    deal
    -0.58
    lund
    -0.57
    POSITIVE LOGITS
    ise
    0.81
    ises
    0.80
     unequ
    0.77
    dden
    0.75
    ISE
    0.69
     differently
    0.68
    ivas
    0.67
     patients
    0.67
     wounded
    0.66
     respectfully
    0.65
    Activations Density 0.043%

    No Known Activations