© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 6623
    Prev
    Next
    INDEX
    Explanations

    non-alphanumeric characters and social media handles

    oai_token-act-pair · gpt-3.5-turbo

    references to social media interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sloven
    -0.87
    arden
    -0.87
    bird
    -0.86
    birds
    -0.83
     sandwiches
    -0.80
     Owl
    -0.78
    Georg
    -0.77
    igators
    -0.76
    owl
    -0.76
    Bird
    -0.76
    POSITIVE LOGITS
     Modi
    1.09
     Harper
    1.09
     Gordon
    1.09
     Sharif
    1.00
    Gordon
    0.99
     PM
    0.96
     HM
    0.95
     Tories
    0.94
     Blair
    0.92
     Tory
    0.91
    Activations Density 0.376%

    No Known Activations