Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 5394
    Prev
    Next
    INDEX
    Explanations

    mentions of environmental responsibility and sustainability

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "this."

    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
    ãĤ¹ãĥĪ
    -0.82
    adle
    -0.77
    ARS
    -0.73
    omo
    -0.72
    anamo
    -0.71
    amia
    -0.71
    avering
    -0.70
    ready
    -0.68
    istries
    -0.68
    Ñĥ
    -0.67
    POSITIVE LOGITS
     guy
    1.03
     week
    0.97
     trope
    0.92
     isn
    0.92
     weekend
    0.91
     year
    0.86
     latest
    0.85
     tactic
    0.84
     happens
    0.84
     article
    0.83
    Activations Density 0.226%

    No Known Activations