© 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. 7-RES-JB
    11. 2218
    Prev
    Next
    INDEX
    Explanations

    instances of refusal or resistance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "refused to," indicating a rejection or non-compliance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.90
    ////////////////////////////////
    -0.79
    quickShipAvailable
    -0.79
     Prediction
    -0.76
    grounds
    -0.70
    nin
    -0.69
    lined
    -0.67
     Lots
    -0.65
    ãĤ¼ãĤ¦ãĤ¹
    -0.63
    Line
    -0.62
    POSITIVE LOGITS
     cooperate
    1.22
     acknowledge
    1.20
     accept
    1.19
     bud
    1.14
     obey
    1.13
     comply
    1.11
     recognize
    1.10
     participate
    1.09
     endorse
    1.07
     negotiate
    1.06
    Activations Density 0.044%

    No Known Activations