© 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. 0-RES-JB
    11. 11831
    Prev
    Next
    INDEX
    Explanations

    phrases related to suspicion or suspicion of criminal activity

    oai_token-act-pair · gpt-3.5-turbo

    references to suspicion and presumption regarding individuals' involvement in various activities or crimes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Save
    -0.75
     Saving
    -0.68
    Write
    -0.65
     blah
    -0.64
    Tokens
    -0.63
    Sum
    -0.62
     Swim
    -0.61
     Create
    -0.60
     Divide
    -0.59
    lust
    -0.59
    POSITIVE LOGITS
     suspected
    3.65
     suspects
    1.88
     presumed
    1.84
     suspect
    1.79
     alleged
    1.70
     accused
    1.65
     suspicious
    1.61
     believed
    1.59
     suspicions
    1.57
     suspicion
    1.53
    Activations Density 0.011%

    No Known Activations