© 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. 10-RES-JB
    11. 11532
    Prev
    Next
    INDEX
    Explanations

    phrases indicating arrests or criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating reasons for arrests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ires
    -0.76
    itle
    -0.72
    atar
    -0.72
    8000
    -0.70
    Options
    -0.69
    eous
    -0.69
    erd
    -0.68
    omics
    -0.67
    soDeliveryDate
    -0.67
    Born
    -0.66
    POSITIVE LOGITS
     violating
    1.39
     breaching
    1.23
    gery
    1.18
     refusing
    1.16
     assaulting
    1.12
     allegedly
    1.12
     interfering
    1.12
     inciting
    1.11
     failing
    1.06
     tresp
    1.06
    Activations Density 0.068%

    No Known Activations