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. 3-RES-JB
    6. 14574
    Prev
    Next
    INDEX
    Explanations

    phrases related to traditional or standard practices

    oai_token-act-pair · gpt-3.5-turbo

    references to conventional designs and practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oning
    -0.78
    gur
    -0.76
    oran
    -0.72
    haw
    -0.71
    hop
    -0.68
    hoff
    -0.67
    ander
    -0.66
    han
    -0.64
     Dalai
    -0.64
     Wanted
    -0.63
    POSITIVE LOGITS
     wisdom
    1.04
    ventional
    0.96
    etheless
    0.87
     conventional
    0.86
    ually
    0.78
    ization
    0.77
    aneously
    0.76
    nesday
    0.76
    idad
    0.76
    arily
    0.75
    Activations Density 0.008%

    No Known Activations