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. 20398
    Prev
    Next
    INDEX
    Explanations

    the word "Completed"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the prefix "com" in words

    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
     firsthand
    -0.66
     harbor
    -0.65
     Icelandic
    -0.64
     inund
    -0.63
     politic
    -0.63
     Refuge
    -0.63
     shatter
    -0.62
     repetitive
    -0.61
     gratification
    -0.60
     caution
    -0.58
    POSITIVE LOGITS
    fortable
    1.36
    puters
    1.35
    pletion
    1.35
    pleting
    1.33
    plement
    1.32
    puting
    1.31
    parable
    1.23
    pleted
    1.22
    mented
    1.18
    plet
    1.18
    Activations Density 0.030%

    No Known Activations