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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 17568
    Prev
    Next
    INDEX
    Explanations

    references to the city "Nagasaki."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Nag" and references to associated characters or events

    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
    -0.92
    terday
    -0.80
    xon
    -0.70
    ++++++++++++++++
    -0.69
    chnology
    -0.69
    clus
    -0.67
     bailed
    -0.62
    200000
    -0.61
     roy
    -0.61
     Serious
    -0.58
    POSITIVE LOGITS
    ril
    1.23
    asaki
    1.21
    oya
    1.07
    rils
    0.99
    orno
    0.98
    ash
    0.96
    atsuki
    0.95
    uru
    0.95
    gy
    0.94
    lins
    0.94
    Activations Density 0.024%

    No Known Activations