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. 8312
    Prev
    Next
    INDEX
    Explanations

    words related to groups or gatherings

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "gro"

    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
    UAL
    -0.74
     Leilan
    -0.67
     innocence
    -0.66
     duly
    -0.64
     CPC
    -0.63
    manship
    -0.60
     PDT
    -0.60
     destroyer
    -0.59
     peril
    -0.58
     Immunity
    -0.58
    POSITIVE LOGITS
    ovy
    1.34
    tesque
    1.19
    aning
    1.14
    tty
    1.14
    tto
    1.13
    veland
    1.10
    ggy
    1.07
    cery
    1.05
    oved
    1.03
    ves
    1.03
    Activations Density 0.027%

    No Known Activations