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. 9391
    Prev
    Next
    INDEX
    Explanations

    mentions of specific entities enclosed in square brackets

    oai_token-act-pair · gpt-3.5-turbo

    references to groups or subjects enclosed in brackets

    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
    ĪĴ
    -0.79
    ĸļ
    -0.79
    ãĤ¢ãĥ«
    -0.69
    ãĤ¶
    -0.67
    -+-+
    -0.67
    ãĥł
    -0.66
    Ͻ
    -0.65
     Socket
    -0.64
    zh
    -0.64
    chen
    -0.63
    POSITIVE LOGITS
    selves
    0.91
    },"
    0.74
    ."[
    0.70
    indust
    0.64
    ...]
    0.61
    thumbnails
    0.61
     Mol
    0.59
    wreck
    0.59
    interface
    0.59
    â̦]
    0.59
    Activations Density 0.071%

    No Known Activations