© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 3486
    Prev
    Next
    INDEX
    Explanations

    phrases related to social issues, injustices, and criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    concerns related to social and systemic issues, particularly those involving discrimination and violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tours
    -0.74
     Investors
    -0.72
    cit
    -0.72
    ohm
    -0.70
    Write
    -0.67
     Ago
    -0.67
     Replacement
    -0.66
    ullivan
    -0.64
    #$
    -0.62
    ãĥĦ
    -0.61
    POSITIVE LOGITS
     rampant
    1.57
     endemic
    1.44
     prevalent
    1.30
     rife
    1.30
     pervasive
    1.24
     tolerated
    1.20
     commonplace
    1.20
     punishable
    1.11
     perpetrated
    1.08
     epidemic
    1.07
    Activations Density 0.247%

    No Known Activations