Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 4752
    Prev
    Next
    INDEX
    Explanations

    words related to vision and sight

    oai_token-act-pair · gpt-3.5-turbo

    the presence of words that contain the string "ight"

    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
    女
    -0.96
    PsyNetMessage
    -0.94
    accompan
    -0.88
    itaire
    -0.81
    qv
    -0.81
    senal
    -0.74
    ãĥīãĥ©ãĤ´ãĥ³
    -0.70
    76561
    -0.70
    berman
    -0.70
    Filename
    -0.68
    POSITIVE LOGITS
    mares
    1.28
    mare
    0.95
    seeing
    0.93
    enment
    0.91
    edly
    0.88
    ened
    0.84
    ful
    0.84
    ead
    0.81
    edIn
    0.81
    eyed
    0.81
    Activations Density 0.025%

    No Known Activations