© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 14462
    Prev
    Next
    INDEX
    Explanations

    words related to violent or harmful actions and medical treatments

    oai_token-act-pair · gpt-3.5-turbo

    themes related to violence and its consequences

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ridor
    -0.54
     haw
    -0.51
     Kot
    -0.50
     mature
    -0.50
     multip
    -0.50
     waivers
    -0.49
     reun
    -0.49
    adobe
    -0.49
     NT
    -0.49
     lett
    -0.49
    POSITIVE LOGITS
    )).
    1.30
    )?
    1.29
    )),
    1.12
    ]).
    1.10
     respectively
    1.10
    ))
    1.05
    ?,
    1.04
    ?).
    1.02
    )))
    1.00
    .?
    0.98
    Activations Density 2.597%

    No Known Activations