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. 12176
    Prev
    Next
    INDEX
    Explanations

    phrases related to commentary or opinions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating connections or relationships between subjects

    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
     ®
    -0.75
     lamented
    -0.68
    ashington
    -0.68
    Requires
    -0.66
    published
    -0.65
    geoning
    -0.65
     reportedly
    -0.65
    ģĸ
    -0.63
    igmatic
    -0.63
    ¶
    -0.63
    POSITIVE LOGITS
     everybody
    1.22
     somebody
    1.15
     ['
    1.12
     stuff
    1.02
     anybody
    1.01
     ..."
    1.01
     ours
    1.00
     somet
    1.00
     â̦"
    1.00
     guys
    0.99
    Activations Density 0.687%

    No Known Activations