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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 14186
    Prev
    Next
    INDEX
    Explanations

    the name "Amanda" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Amanda."

    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
    direction
    -0.77
    vous
    -0.73
    safety
    -0.72
    book
    -0.71
    roups
    -0.70
    lag
    -0.69
    shadow
    -0.69
    perse
    -0.67
    grading
    -0.67
    istry
    -0.67
    POSITIVE LOGITS
     Berry
    1.05
     Amanda
    1.00
     Knox
    0.94
     Matthews
    0.90
     Todd
    0.86
    gdala
    0.80
     Carter
    0.80
     Nunes
    0.80
     Joyce
    0.79
     Bradley
    0.79
    Activations Density 0.010%

    No Known Activations