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. 3598
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and tools, particularly ones that involve visual elements or textual components

    oai_token-act-pair · gpt-3.5-turbo

    various elements related tovisual content, data representation, and structures

    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
    oÄŁ
    -0.43
    asus
    -0.43
    BUG
    -0.42
     Tycoon
    -0.41
    Args
    -0.40
    shield
    -0.40
    SOURCE
    -0.39
     Inquiry
    -0.39
    atorium
    -0.39
     Avalanche
    -0.39
    POSITIVE LOGITS
    hips
    1.16
    mith
    1.12
    hip
    1.09
    paces
    1.08
    poons
    1.03
    pace
    1.03
    pring
    1.02
    uggest
    1.02
    hops
    0.95
    ettings
    0.94
    Activations Density 0.981%

    No Known Activations