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. 8007
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers with a specific pattern

    oai_token-act-pair · gpt-3.5-turbo

    numeric values, specifically those that correspond to the number 2

    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
    awaru
    -0.87
    rolet
    -0.79
    efully
    -0.72
    etz
    -0.70
    otle
    -0.68
    gerald
    -0.67
    iership
    -0.66
     Ik
    -0.64
    uated
    -0.63
    lehem
    -0.62
    POSITIVE LOGITS
    nd
    1.84
    ND
    1.04
     thirds
    0.98
    160
    0.96
    147
    0.93
    187
    0.91
    133
    0.91
    ½
    0.91
    245
    0.90
    155
    0.87
    Activations Density 0.123%

    No Known Activations