Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 21106
    Prev
    Next
    INDEX
    Explanations

    mentions of government and international organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to government or official entities and their statements

    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
    tle
    -0.78
    worn
    -0.77
    atable
    -0.77
    pler
    -0.74
    arrow
    -0.71
    los
    -0.70
    potion
    -0.68
    vable
    -0.68
    ingen
    -0.68
    isSpecialOrderable
    -0.68
    POSITIVE LOGITS
     ministry
    1.41
     Ministry
    1.38
     Interior
    1.31
     Organisation
    1.22
     interior
    1.21
     ministries
    1.14
     prosecutor
    1.13
     Directorate
    1.12
     Organization
    1.11
     judiciary
    1.10
    Activations Density 0.250%

    No Known Activations