© 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. 1663
    Prev
    Next
    INDEX
    Explanations

    phrases related to secret or hidden actions and intentions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to stealth or covert actions

    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
    ĵĺ
    -0.84
     Pwr
    -0.82
    rices
    -0.82
    onial
    -0.81
    rises
    -0.78
    minus
    -0.72
    nan
    -0.72
    rification
    -0.71
    oros
    -0.70
    wo
    -0.70
    POSITIVE LOGITS
     sneak
    0.95
    ily
    0.86
     peek
    0.83
    door
    0.76
    atory
    0.71
    hold
    0.71
     sne
    0.71
     glances
    0.69
     Sne
    0.67
    away
    0.66
    Activations Density 0.045%

    No Known Activations