© 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 EvalsExportsinterp-engineNEWAPI 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. 23107
    Prev
    Next
    INDEX
    Explanations

    phrases related to consent, knowledge, and permission in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to consent and knowledge regarding actions taken without proper authorization

    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
    ahime
    -0.93
    ãĥ³ãĤ¸
    -0.84
    ãĥĩ
    -0.77
    estate
    -0.74
    ãĥ¼ãĤ¯
    -0.70
     Offline
    -0.69
    ãĥ´
    -0.67
    late
    -0.67
    inous
    -0.65
    geist
    -0.65
    POSITIVE LOGITS
     permission
    1.18
     supervision
    1.04
     knowledge
    1.02
     assistance
    1.01
     consent
    1.01
     noticing
    0.97
     slightest
    0.92
     approval
    0.91
     knowing
    0.91
     pesky
    0.89
    Activations Density 0.154%

    No Known Activations