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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 21759
    Prev
    Next
    INDEX
    Explanations

    names of people, primarily focusing on the name "Miranda"

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals associated with significant political or legal contexts

    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
    gery
    -0.86
    Commerce
    -0.85
    nan
    -0.82
    mail
    -0.79
    lap
    -0.78
    yssey
    -0.75
    liness
    -0.74
    Operation
    -0.73
    Rew
    -0.72
    RESULTS
    -0.72
    POSITIVE LOGITS
     Sturgeon
    0.93
    ña
    0.78
    ussen
    0.76
     Miranda
    0.76
     Kats
    0.70
     Nicola
    0.69
    ignt
    0.69
    ño
    0.67
    obyl
    0.67
    izations
    0.67
    Activations Density 0.023%

    No Known Activations