© 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. 0-RES-JB
    6. 22619
    Prev
    Next
    INDEX
    Explanations

    references to government-related entities or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to government entities and discussions related to governmental actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Myr
    -0.79
    uckle
    -0.69
     matchups
    -0.68
    »Ĵ
    -0.67
     opener
    -0.66
    enne
    -0.65
    yy
    -0.65
    edit
    -0.64
     hey
    -0.64
    linger
    -0.63
    POSITIVE LOGITS
     Government
    3.66
    Government
    2.75
     Governments
    2.61
     government
    2.33
    government
    2.24
     governmental
    1.72
     governments
    1.71
     Ministers
    1.57
     Federal
    1.56
    Federal
    1.54
    Activations Density 0.014%

    No Known Activations