© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 21097
    Prev
    Next
    INDEX
    Explanations

    phrases related to suspicion and police activity

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to suspicion and criminal activity

    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
    skill
    -0.74
    anche
    -0.72
    hare
    -0.72
    ourses
    -0.70
    jri
    -0.68
    psey
    -0.68
    sburg
    -0.68
    learning
    -0.68
    church
    -0.67
    wake
    -0.67
    POSITIVE LOGITS
    lessly
    0.85
     suspicious
    0.81
     suspects
    0.76
     suspect
    0.76
     motives
    0.69
     arson
    0.68
     suspicion
    0.67
     Activity
    0.67
    ostic
    0.66
    worthiness
    0.66
    Activations Density 0.039%

    No Known Activations