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. 21790
    Prev
    Next
    INDEX
    Explanations

    phrases related to justification or explanation of actions

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "for the sake of."

    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
    sbm
    -0.63
    ibr
    -0.61
     corrid
    -0.59
    bor
    -0.54
     Fired
    -0.54
    odes
    -0.53
    interstitial
    -0.52
    odge
    -0.52
    taboola
    -0.52
     basement
    -0.52
    POSITIVE LOGITS
     sake
    1.10
    resy
    0.89
    istical
    0.80
    lihood
    0.73
    ¬¼
    0.73
     thereof
    0.71
    farious
    0.71
    oldown
    0.70
    atsu
    0.70
    FTWARE
    0.70
    Activations Density 0.028%

    No Known Activations