© 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. 23082
    Prev
    Next
    INDEX
    Explanations

    phrases related to investigations or inquiries

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to police investigations

    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
    ãĤª
    -0.83
    Downloadha
    -0.70
    å§
    -0.66
     Democr
    -0.65
     badass
    -0.63
     ain
    -0.62
     despised
    -0.61
    å¥
    -0.61
     belonged
    -0.59
    âĹ¼
    -0.59
    POSITIVE LOGITS
     feasibility
    0.83
    ossible
    0.80
     possible
    0.80
     allegations
    0.76
     enqu
    0.75
     mediation
    0.73
     Possible
    0.72
    umar
    0.72
     urgently
    0.71
     reports
    0.70
    Activations Density 0.444%

    No Known Activations