© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 967
    Prev
    Next
    INDEX
    Explanations

    words related to criminal behavior and legal penalties

    oai_token-act-pair · gpt-3.5-turbo

    terms related to criminal behavior and offenders

    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
     Maiden
    -0.69
    Ħ¢
    -0.69
    thur
    -0.67
     stopp
    -0.67
     Airl
    -0.66
    printed
    -0.64
    emin
    -0.61
    ahon
    -0.60
    HAHA
    -0.60
    Mount
    -0.60
    POSITIVE LOGITS
     addicted
    0.89
     mastermind
    0.87
     incarcerated
    0.87
     gangs
    0.85
     sentenced
    0.85
     offenders
    0.85
     prey
    0.84
     traff
    0.84
     offender
    0.83
     beware
    0.82
    Activations Density 0.081%

    No Known Activations