© 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. 9-RES-JB
    11. 15983
    Prev
    Next
    INDEX
    Explanations

    phrases related to rule-breaking or bending social norms

    oai_token-act-pair · gpt-3.5-turbo

    negative phrases or statements

    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
     caution
    -0.67
     flirt
    -0.67
     Dickinson
    -0.67
     Arabian
    -0.65
     hiber
    -0.64
     pomp
    -0.62
     shares
    -0.61
     curtain
    -0.61
     troop
    -0.60
     adm
    -0.60
    POSITIVE LOGITS
    turned
    1.29
    cum
    1.17
    sama
    1.14
    selves
    1.13
    sized
    1.12
    style
    1.12
    related
    1.11
    type
    1.06
    induced
    1.05
    san
    1.04
    Activations Density 0.164%

    No Known Activations