© 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. 8-RES-JB
    11. 12394
    Prev
    Next
    INDEX
    Explanations

    words related to flaws, inaccuracies, and societal issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases that imply systemic issues or criticisms of societal structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •contextual features
    fires on the last word of e.g., "reports are misleading" and "is fundamentally flawed"

    No Comments

    Negative Logits
    emetery
    -0.55
    elve
    -0.53
    avia
    -0.49
     advoc
    -0.47
     Instr
    -0.47
    oqu
    -0.47
    oslov
    -0.46
    rive
    -0.45
    iona
    -0.45
    Chart
    -0.45
    POSITIVE LOGITS
     ):
    1.12
     )
    1.05
     ),
    1.01
     ]
    0.99
     ,"
    0.97
     );
    0.97
    ↵Âł
    0.96
     ,
    0.91
     ;
    0.89
     ).
    0.87
    Activations Density 1.437%

    No Known Activations