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

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 5353
    Prev
    Next
    INDEX
    Explanations

    instances where demands or requests are made with authority

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express demands or requests for action

    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
    ãĥŃ
    -0.85
     srf
    -0.77
    nown
    -0.77
    sin
    -0.77
    Ń·
    -0.73
    ãĥ³ãĤ¸
    -0.73
     pione
    -0.73
    swick
    -0.71
    NetMessage
    -0.70
    ãĥĦ
    -0.69
    POSITIVE LOGITS
     answers
    1.00
     clarification
    1.00
     repayment
    0.92
     accountability
    0.92
     retribution
    0.90
     payment
    0.88
     acknowledgement
    0.87
     obedience
    0.86
     explanations
    0.86
     immediate
    0.86
    Activations Density 0.065%

    No Known Activations