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. 6429
    Prev
    Next
    INDEX
    Explanations

    specific actions or observations within a sentence, such as noticing, discovering, or finding

    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
    youtube
    -0.68
    ula
    -0.66
    ugal
    -0.65
    hattan
    -0.62
    charge
    -0.62
    duty
    -0.61
    href
    -0.61
    raviolet
    -0.61
    phrine
    -0.61
    osc
    -0.60
    POSITIVE LOGITS
     unmist
    0.90
     similarities
    0.88
     how
    0.83
     nothing
    0.82
     what
    0.81
     none
    0.80
     plenty
    0.79
     myriad
    0.79
     something
    0.79
     startling
    0.78
    Activations Density 0.267%

    No Known Activations