© 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 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. 0-RES-JB
    11. 12653
    Prev
    Next
    INDEX
    Explanations

    legal terms, such as 'punitive', 'compensatory', and 'exemplary'

    oai_token-act-pair · gpt-3.5-turbo

    references to punitive actions or measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ews
    -0.76
    Mo
    -0.63
    egg
    -0.63
     Legend
    -0.63
     Connect
    -0.63
    nect
    -0.62
     legend
    -0.62
    cloud
    -0.62
    omen
    -0.62
    Cloud
    -0.62
    POSITIVE LOGITS
     punitive
    3.76
     retali
    1.38
     punishing
    1.34
     coercive
    1.34
     punishments
    1.32
     punishment
    1.27
     draconian
    1.26
     deterrent
    1.25
     penal
    1.23
     retribution
    1.18
    Activations Density 0.024%

    No Known Activations