© 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. 10-RES-JB
    11. 7886
    Prev
    Next
    INDEX
    Explanations

    sentences related to legal sentencing and imprisonment

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to prison sentences and incarceration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    selves
    -0.77
    ãĤ¡
    -0.72
     Participant
    -0.68
    Override
    -0.68
    matic
    -0.65
     enqu
    -0.63
     wip
    -0.63
    ById
    -0.61
    å¹
    -0.60
    ãĤ´ãĥ³
    -0.60
    POSITIVE LOGITS
     prison
    1.70
     jail
    1.55
    prison
    1.36
     incarceration
    1.22
     confinement
    1.15
     imprisonment
    1.15
     prisons
    1.14
     detention
    1.11
     captivity
    1.08
     Jail
    1.07
    Activations Density 0.038%

    No Known Activations