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. 16040
    Prev
    Next
    INDEX
    Explanations

    quotations or reported statements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to official statements and governmental actions

    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
     amalg
    -0.77
     corrid
    -0.71
    xual
    -0.70
     metab
    -0.67
     Cth
    -0.66
     pigeon
    -0.66
     ali
    -0.65
    phant
    -0.65
     mould
    -0.65
     stub
    -0.65
    POSITIVE LOGITS
    Secretary
    1.40
     White
    1.33
     Secretary
    1.32
     Spicer
    1.30
     Treasury
    1.30
    White
    1.28
     Pentagon
    1.25
    Senate
    1.25
     President
    1.24
     Obama
    1.24
    Activations Density 0.617%

    No Known Activations