© 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. 12624
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases related to police reports or criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    punctuated phrases indicating incidents or events

    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
    NetMessage
    -0.81
    reprene
    -0.75
    matically
    -0.74
    ongevity
    -0.73
     treaties
    -0.69
    orem
    -0.69
     utopian
    -0.67
    omics
    -0.66
    estine
    -0.65
    agine
    -0.64
    POSITIVE LOGITS
     according
    1.07
     prompting
    0.99
     TMZ
    0.89
    according
    0.89
     Sgt
    0.82
     screamed
    0.80
     pictured
    0.79
     injuring
    0.79
     paramedics
    0.77
     yelled
    0.76
    Activations Density 0.383%

    No Known Activations