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. 14784
    Prev
    Next
    INDEX
    Explanations

    references to locations or organizations named "Crossroads"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Crossroads" and related contexts

    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
     subp
    -0.78
    Ĥİ
    -0.77
    ifer
    -0.74
    fecture
    -0.73
    oran
    -0.73
    aution
    -0.72
    ©¶æ¥µ
    -0.70
    ishment
    -0.69
    Ł
    -0.67
    Ĥ
    -0.66
    POSITIVE LOGITS
    roads
    1.03
     Roads
    0.83
    clinton
    0.77
     Bike
    0.77
     Prayer
    0.71
    ä½ľ
    0.71
    ãĤ¤ãĥĪ
    0.69
    è¦
    0.68
    NetMessage
    0.67
    loading
    0.66
    Activations Density 0.021%

    No Known Activations