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. 9-RES-JB
    6. 6431
    Prev
    Next
    INDEX
    Explanations

    information related to actions and achievements, such as authoring, passing, featuring, signing, printing, and opening

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cum
    -0.72
    itus
    -0.64
    fml
    -0.63
    >]
    -0.63
    ahu
    -0.62
    usal
    -0.62
     largeDownload
    -0.61
    Solution
    -0.61
    iso
    -0.60
    ibe
    -0.59
    POSITIVE LOGITS
     innumerable
    1.67
     countless
    1.66
     numerous
    1.62
     dozens
    1.53
     many
    1.48
     hundreds
    1.44
     myriad
    1.43
     lots
    1.32
     several
    1.30
     thousands
    1.26
    Activations Density 1.223%

    No Known Activations