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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 7-RES-JB
    6. 4475
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to international studies

    oai_token-act-pair · gpt-3.5-turbo

    elements related to international entities or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ruary
    -0.97
    ufact
    -0.73
    ocre
    -0.72
    ensical
    -0.71
    abase
    -0.69
    steen
    -0.69
    enhagen
    -0.66
    xon
    -0.64
     jelly
    -0.60
     tune
    -0.59
    POSITIVE LOGITS
    ®
    0.92
    Ĩ
    0.85
    Dispatch
    0.75
    ³
    0.75
    Ń
    0.74
    ¡
    0.74
    Ģ
    0.73
     Shogun
    0.73
    士
    0.72
    ¯
    0.71
    Activations Density 0.269%

    No Known Activations