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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 22416
    Prev
    Next
    INDEX
    Explanations

    phrases related to giving in or yielding

    oai_token-act-pair · gpt-3.5-turbo

    past tense verbs related to saving or protecting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inian
    -0.65
     Scand
    -0.65
     Kry
    -0.64
    jen
    -0.63
    ivity
    -0.61
    VA
    -0.61
     QC
    -0.60
    ica
    -0.59
     WATCHED
    -0.58
     Bus
    -0.57
    POSITIVE LOGITS
    igger
    0.80
    kered
    0.79
    ettle
    0.71
    ĸļ
    0.67
    oots
    0.67
    etheless
    0.66
    Ń·
    0.66
     up
    0.64
    NetMessage
    0.64
    ulously
    0.64
    Activations Density 0.135%

    No Known Activations