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. 4-RES-JB
    6. 21474
    Prev
    Next
    INDEX
    Explanations

    words related to praise or admiration

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "glory" and its variations

    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
    BOOK
    -0.86
    heter
    -0.67
    irin
    -0.67
    ANY
    -0.66
    strong
    -0.65
    ------------------------------------------------
    -0.64
    artment
    -0.62
    JUST
    -0.61
    esthetic
    -0.60
    joining
    -0.60
    POSITIVE LOGITS
     glory
    1.05
     Glory
    0.87
    ful
    0.80
    ifully
    0.80
    sburg
    0.80
    fully
    0.79
    eous
    0.78
    ous
    0.75
    stone
    0.74
     Trophy
    0.73
    Activations Density 0.010%

    No Known Activations