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. 19194
    Prev
    Next
    INDEX
    Explanations

    numbers with high values

    oai_token-act-pair · gpt-3.5-turbo

    numerical values, particularly large numbers and monetary amounts

    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
    orate
    -0.82
    lict
    -0.81
    bara
    -0.80
    inges
    -0.79
    nels
    -0.76
    essa
    -0.76
    acia
    -0.74
    lying
    -0.74
    inately
    -0.74
    nih
    -0.73
    POSITIVE LOGITS
     ILCS
    0.98
     MHz
    0.94
    SourceFile
    0.81
    æ©Ł
    0.80
    MHz
    0.79
    576
    0.71
    OPLE
    0.71
    bps
    0.70
    ãĥ³ãĤ¸
    0.70
    6666
    0.67
    Activations Density 0.055%

    No Known Activations