© 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. 2-RES-JB
    11. 17269
    Prev
    Next
    INDEX
    Explanations

    instances of the word "arrests" in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of arrests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yss
    -0.68
    vironment
    -0.61
    psons
    -0.59
    reen
    -0.59
    learning
    -0.58
    Myth
    -0.58
    WE
    -0.58
     enthus
    -0.57
     Mon
    -0.57
    wb
    -0.56
    POSITIVE LOGITS
     arrests
    0.99
     arrest
    0.87
     Arrest
    0.74
     arrested
    0.73
    onto
    0.73
     decriminal
    0.69
    oppable
    0.69
     detain
    0.68
    eering
    0.68
     quotas
    0.65
    Activations Density 0.009%

    No Known Activations