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. 8-RES-JB
    6. 19199
    Prev
    Next
    INDEX
    Explanations

    places or locations where events occurred

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "where."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TE
    -0.66
    ve
    -0.63
    '/
    -0.62
    âĵĺ
    -0.60
    Que
    -0.60
    Kind
    -0.59
    idia
    -0.58
    Think
    -0.58
    tty
    -0.57
    unes
    -0.56
    POSITIVE LOGITS
    upon
    1.77
     they
    0.91
    soever
    0.86
     he
    0.81
    abouts
    0.80
    after
    0.72
     she
    0.69
    fore
    0.68
     temperatures
    0.67
     it
    0.67
    Activations Density 0.052%

    No Known Activations