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. 10332
    Prev
    Next
    INDEX
    Explanations

    phrases related to existence or longevity

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "around" in various contexts indicating time or presence

    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
    xual
    -0.84
    oÄŁ
    -0.67
    deal
    -0.67
    ascript
    -0.66
    istle
    -0.65
    phrine
    -0.64
     Dalai
    -0.63
    hetical
    -0.63
    ithing
    -0.62
    BT
    -0.61
    POSITIVE LOGITS
    abouts
    0.74
     corners
    0.73
     here
    0.67
     alot
    0.66
     alright
    0.63
    anism
    0.63
     anymore
    0.62
     town
    0.60
    here
    0.60
     ok
    0.60
    Activations Density 0.032%

    No Known Activations