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. 5-RES-JB
    6. 16572
    Prev
    Next
    INDEX
    Explanations

    verbs related to legal processes or actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to negotiation and legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulner
    -0.69
    ilers
    -0.62
    switch
    -0.62
    ortium
    -0.62
    eco
    -0.62
    iris
    -0.61
    amy
    -0.59
    hitting
    -0.59
    eele
    -0.57
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.57
    POSITIVE LOGITS
    urally
    0.77
    ially
    0.76
    zzle
    0.67
    LY
    0.64
     against
    0.64
    NESS
    0.64
     advising
    0.63
    OTUS
    0.63
    ly
    0.63
    enance
    0.62
    Activations Density 0.149%

    No Known Activations