© 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. 11-RES-JB
    11. 24131
    Prev
    Next
    INDEX
    Explanations

    mentions of legal convictions resulting in imprisonment

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to prison sentences

    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
    wcsstore
    -0.78
    [_
    -0.68
    natureconservancy
    -0.68
    selves
    -0.67
     Unsure
    -0.65
    Override
    -0.64
    ONSORED
    -0.64
    Completed
    -0.63
    catentry
    -0.62
    nce
    -0.62
    POSITIVE LOGITS
     prison
    1.64
     jail
    1.50
    prison
    1.34
     confinement
    1.11
     captivity
    1.10
     custody
    1.09
     Prison
    1.08
     prisons
    1.07
     incarceration
    1.07
     imprisonment
    1.06
    Activations Density 0.046%

    No Known Activations