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. 3-RES-JB
    6. 11737
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Sessions."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Sessions."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     VID
    -0.66
    OPS
    -0.65
    lihood
    -0.63
    ocard
    -0.63
     Squid
    -0.63
    oard
    -0.62
     pity
    -0.62
    bably
    -0.62
    Ķ
    -0.62
     dism
    -0.61
    POSITIVE LOGITS
     Sessions
    1.14
    essions
    0.89
    esson
    0.84
    achus
    0.84
    nyder
    0.83
    acre
    0.81
    lain
    0.81
    gren
    0.80
    agne
    0.78
    alty
    0.73
    Activations Density 0.005%

    No Known Activations