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. 10523
    Prev
    Next
    INDEX
    Explanations

    words related to speed or rate of change

    oai_token-act-pair · gpt-3.5-turbo

    adverbs that indicate speed or intensity of actions

    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
    tein
    -0.68
    izoph
    -0.64
    oln
    -0.64
    vous
    -0.64
    cknowled
    -0.63
    icion
    -0.61
     History
    -0.61
    ription
    -0.56
    oute
    -0.56
    oked
    -0.56
    POSITIVE LOGITS
     srfAttach
    0.98
     during
    0.76
     because
    0.76
     throughout
    0.76
     onstage
    0.75
     (>
    0.72
    aneously
    0.71
     unnoticed
    0.70
     thereafter
    0.70
     afterward
    0.70
    Activations Density 0.217%

    No Known Activations