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. 21287
    Prev
    Next
    INDEX
    Explanations

    locations or places

    oai_token-act-pair · gpt-3.5-turbo

    locations or places mentioned in the text

    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
    hemy
    -0.78
    henko
    -0.71
     VIDEOS
    -0.63
    rang
    -0.63
     datas
    -0.63
    ratulations
    -0.62
     enrol
    -0.61
     %%
    -0.61
    $$
    -0.61
     unemploy
    -0.61
    POSITIVE LOGITS
    patient
    1.08
     conjunction
    1.08
     lieu
    1.06
     southwest
    0.98
    efficiency
    0.95
     southeastern
    0.94
     Switzerland
    0.94
     accordance
    0.94
     southwestern
    0.94
     Normandy
    0.90
    Activations Density 0.201%

    No Known Activations