© 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. 9789
    Prev
    Next
    INDEX
    Explanations

    mentions of law enforcement and criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of law enforcement entities and their activities

    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
     %%
    -0.63
    ecast
    -0.63
     torch
    -0.62
    oths
    -0.61
    ictional
    -0.60
    eday
    -0.60
    atible
    -0.59
    ²¾
    -0.59
     flowering
    -0.58
    -+-+
    -0.58
    POSITIVE LOGITS
     said
    1.15
    said
    1.09
     says
    1.01
     Says
    0.89
     wrote
    0.87
     SAY
    0.85
     explained
    0.84
     told
    0.83
     joked
    0.81
     screamed
    0.80
    Activations Density 0.337%

    No Known Activations