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. 5-RES-JB
    6. 20064
    Prev
    Next
    INDEX
    Explanations

    references to teachers and educators

    oai_token-act-pair · gpt-3.5-turbo

    references to teachers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rils
    -0.88
    tera
    -0.74
    ril
    -0.74
    axy
    -0.65
    hawks
    -0.65
    rencies
    -0.64
     launchers
    -0.63
    00200000
    -0.62
    obin
    -0.62
    ulence
    -0.62
    POSITIVE LOGITS
    girls
    0.92
     Teachers
    0.88
     Teacher
    0.85
    heet
    0.82
     teacher
    0.81
    children
    0.78
    achers
    0.75
    student
    0.75
    girl
    0.75
     teachers
    0.74
    Activations Density 0.028%

    No Known Activations