© 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. 23627
    Prev
    Next
    INDEX
    Explanations

    mentions of possession of illegal items or substances, particularly for criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to possession of illegal substances or weapons

    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
    htt
    -0.71
    prep
    -0.67
    marg
    -0.66
    mitt
    -0.66
    MQ
    -0.65
    κ
    -0.64
    Sil
    -0.62
     subcontract
    -0.62
    senal
    -0.61
    RFC
    -0.60
    POSITIVE LOGITS
     possession
    0.91
    ivity
    0.91
    iture
    0.86
    alogue
    0.85
    ership
    0.84
    ive
    0.83
    iveness
    0.82
    ibles
    0.80
    ession
    0.79
    essors
    0.78
    Activations Density 0.034%

    No Known Activations