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. 2041
    Prev
    Next
    INDEX
    Explanations

    instances where a number is associated with a unit of measurement

    oai_token-act-pair · gpt-3.5-turbo

    phrases or terms indicative of possession or ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    pmwiki
    -0.85
     jurisd
    -0.76
    oiler
    -0.71
    bid
    -0.70
    wcsstore
    -0.67
    REF
    -0.66
    ographical
    -0.66
    displayText
    -0.65
    uyomi
    -0.65
     rul
    -0.64
    POSITIVE LOGITS
     each
    0.88
     FIG
    0.79
     the
    0.74
     sorts
    0.74
     our
    0.69
     these
    0.69
     mankind
    0.68
     any
    0.67
     every
    0.67
     Plants
    0.66
    Activations Density 0.246%

    No Known Activations