© 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. 18236
    Prev
    Next
    INDEX
    Explanations

    words related to surveillance and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words related to surveillance

    oai_token-act-pair · gpt-3.5-turbo
    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
     showers
    -0.69
    asso
    -0.64
     GOODMAN
    -0.61
    £ı
    -0.60
    assian
    -0.60
    artifacts
    -0.59
     flyers
    -0.59
    amiya
    -0.58
    ologically
    -0.57
     rook
    -0.57
    POSITIVE LOGITS
    illance
    1.38
    ttes
    1.19
    tsky
    1.16
    llers
    1.15
    lling
    1.14
    mber
    1.14
    ller
    1.13
    ctors
    1.11
    tta
    1.10
    tti
    1.10
    Activations Density 0.049%

    No Known Activations