© 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
    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. 8941
    Prev
    Next
    INDEX
    Explanations

    phrases related to incarceration and prison conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to incarceration and the justice system

    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
    eday
    -0.92
    fare
    -0.89
    kat
    -0.84
    kies
    -0.84
    child
    -0.83
    edom
    -0.81
    tsky
    -0.78
    fal
    -0.76
    ieu
    -0.74
    fold
    -0.73
    POSITIVE LOGITS
    uating
    0.94
    uted
    0.80
    uate
    0.80
    uated
    0.79
    uation
    0.79
    uting
    0.77
    uations
    0.75
    uates
    0.74
    urations
    0.71
     Powers
    0.70
    Activations Density 0.088%

    No Known Activations