© 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. 11147
    Prev
    Next
    INDEX
    Explanations

    phrases related to public health policy, specifically focusing on the treatment of drug problems as a health issue rather than a criminal issue

    oai_token-act-pair · gpt-3.5-turbo

    the framing of drug problems as health issues rather than criminal issues

    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
    yout
    -0.79
     \"
    -0.77
    ðŁĺ
    -0.77
     tho
    -0.75
    ADVERTISEMENT
    -0.71
    âĢ
    -0.71
    }}}
    -0.70
     behav
    -0.69
     congr
    -0.68
    lol
    -0.66
    POSITIVE LOGITS
     firsthand
    0.94
    rather
    0.80
     differently
    0.77
     anew
    0.76
     intimately
    0.75
     rather
    0.72
     longer
    0.71
    gger
    0.71
     sooner
    0.68
     precisely
    0.65
    Activations Density 1.206%

    No Known Activations