© 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. 12-RES-JB
    11. 3514
    Prev
    Next
    INDEX
    Explanations

    descriptions of incidents involving law enforcement

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to off-duty police officers involved in incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     layoffs
    -0.73
     aftermath
    -0.68
     Valkyrie
    -0.67
     percentile
    -0.67
     demolition
    -0.66
     defeat
    -0.66
     refugees
    -0.65
     Conquest
    -0.65
     onward
    -0.64
     struggle
    -0.63
    POSITIVE LOGITS
    limits
    1.58
    duty
    1.48
    campus
    1.46
    season
    1.42
    chance
    1.39
    camera
    1.37
    kil
    1.36
    label
    1.33
    topic
    1.32
    road
    1.32
    Activations Density 0.015%

    No Known Activations