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. 11-RES-JB
    6. 24349
    Prev
    Next
    INDEX
    Explanations

    hashtags and social media activism phrases

    oai_token-act-pair · gpt-3.5-turbo

    mentions of social media trends and campaigns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     outset
    -0.87
     substitute
    -0.85
     theoretical
    -0.82
     narrator
    -0.80
     stem
    -0.80
     attendant
    -0.80
     vantage
    -0.79
     range
    -0.78
     compress
    -0.78
     formerly
    -0.78
    POSITIVE LOGITS
    Fail
    1.60
    Ban
    1.59
    Know
    1.58
    Mem
    1.56
    Days
    1.56
    Party
    1.56
    Years
    1.54
    Army
    1.53
    Deb
    1.52
    Shut
    1.51
    Activations Density 0.130%

    No Known Activations