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. 7-RES-JB
    6. 20460
    Prev
    Next
    INDEX
    Explanations

    phrases related to permanence or finality

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "for good" in various contexts

    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
    olate
    -0.85
    ocene
    -0.78
    lets
    -0.71
    pper
    -0.70
    ulhu
    -0.68
    aturated
    -0.67
    agonal
    -0.66
    ategory
    -0.65
     Sturgeon
    -0.65
    kson
    -0.64
    POSITIVE LOGITS
     intentions
    0.96
     luck
    0.92
    enough
    0.91
    reads
    0.85
     ol
    0.83
     deeds
    0.82
     deed
    0.81
     Samar
    0.81
    weather
    0.75
    spr
    0.75
    Activations Density 0.078%

    No Known Activations