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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 16456
    Prev
    Next
    INDEX
    Explanations

    phrases where someone is calling for a specific action from others, often involving authorities or organizations

    oai_token-act-pair · gpt-3.5-turbo

    instances of calls to action or requests directed at a specific audience or group

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VERTISEMENT
    -0.81
    vable
    -0.75
    igmatic
    -0.72
    mol
    -0.70
     pione
    -0.70
    ãĤ¨ãĥ«
    -0.70
    puted
    -0.69
    apes
    -0.66
    vance
    -0.65
    amac
    -0.65
    POSITIVE LOGITS
     Congress
    0.99
     lawmakers
    0.97
     policymakers
    0.97
     legislators
    0.94
     governments
    0.89
     congress
    0.88
     ministers
    0.88
     parliament
    0.87
     colleagues
    0.86
     MPs
    0.85
    Activations Density 0.063%

    No Known Activations