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. 0-RES-JB
    6. 21260
    Prev
    Next
    INDEX
    Explanations

    instances of the word "verbose" in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ose," likely indicating a focus on terminology related to medical, biological, or chemical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kitchen
    -0.69
     custody
    -0.62
     Feder
    -0.60
     gig
    -0.60
     proced
    -0.59
     Bethesda
    -0.59
     compet
    -0.58
    WORK
    -0.58
     Nerd
    -0.57
     peer
    -0.57
    POSITIVE LOGITS
    ose
    4.57
    oses
    2.45
    OSE
    2.36
    osing
    2.00
    osed
    1.98
    osity
    1.96
    osen
    1.74
    oser
    1.71
    osa
    1.56
    oso
    1.33
    Activations Density 0.006%

    No Known Activations