© 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. 3535
    Prev
    Next
    INDEX
    Explanations

    phrases related to a police investigation

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

    phrases related to criminal activity and investigations

    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
     favors
    -0.79
    kefeller
    -0.77
     favoring
    -0.75
     Nielsen
    -0.72
     Berman
    -0.72
    Congress
    -0.72
     nonpartisan
    -0.72
     Legislature
    -0.70
     favor
    -0.69
    Pg
    -0.69
    POSITIVE LOGITS
     CCTV
    1.14
    intendent
    1.08
     enqu
    1.06
     gard
    1.04
     BST
    0.97
     999
    0.95
    Officers
    0.91
     Constable
    0.89
     paramedics
    0.88
    ordon
    0.85
    Activations Density 0.345%

    No Known Activations