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. 6-RES-JB
    6. 21159
    Prev
    Next
    INDEX
    Explanations

    words related to a specific location, possibly referring to a town named "Pilsen."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Pilsen" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    İĭ
    -0.85
    yssey
    -0.85
    ¥ŀ
    -0.84
    etheless
    -0.84
    ¥µ
    -0.77
    ĵĺ
    -0.77
    ij士
    -0.76
    ©¶æ¥µ
    -0.75
    \\\\\\\\
    -0.74
     unden
    -0.74
    POSITIVE LOGITS
    Ãł
    0.84
    andom
    0.83
    uminati
    0.82
    inx
    0.81
    aries
    0.81
    iblings
    0.79
    waukee
    0.73
    ogical
    0.72
    borough
    0.71
    arial
    0.71
    Activations Density 0.030%

    No Known Activations