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. 8-RES-JB
    6. 22195
    Prev
    Next
    INDEX
    Explanations

    words related to reciprocal movement or actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "back and forth"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ZA
    -0.78
    ãĤª
    -0.77
    ible
    -0.68
    DX
    -0.67
    ACP
    -0.67
    ĨĴ
    -0.66
    BTC
    -0.65
    ingu
    -0.64
    GMT
    -0.62
    ibly
    -0.62
    POSITIVE LOGITS
     forth
    1.33
    romeda
    0.86
     Forth
    0.78
     throats
    0.77
    forth
    0.74
     throat
    0.69
     Palest
    0.59
     necks
    0.59
     sideways
    0.59
    alus
    0.59
    Activations Density 0.144%

    No Known Activations