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

    Neuronpedia

    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. 10-RES-JB
    11. 8227
    Prev
    Next
    INDEX
    Explanations

    words related to disciplinary actions or punishments

    oai_token-act-pair · gpt-3.5-turbo

    terms related to physical punishment and discipline

    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
    ĪĴ
    -0.77
    Ô
    -0.74
    variable
    -0.73
    ãĥ´
    -0.72
    ivot
    -0.71
    ģ«
    -0.70
    spring
    -0.69
    umm
    -0.68
    herty
    -0.67
    unique
    -0.67
    POSITIVE LOGITS
     techniques
    1.20
     etiquette
    1.08
     rituals
    1.05
     practices
    0.99
     ceremonies
    0.97
     sessions
    0.93
     tactics
    0.93
     procedures
    0.92
     machines
    0.91
     occurs
    0.91
    Activations Density 0.280%

    No Known Activations