© 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. 15105
    Prev
    Next
    INDEX
    Explanations

    phrases related to regulations or instructions

    oai_token-act-pair · gpt-3.5-turbo

    legislative terms and concepts related to restrictions and regulations

    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
    ï¸ı
    -0.85
    terness
    -0.76
    âĹ¼
    -0.75
    çĶ°
    -0.74
    _.
    -0.71
    Mom
    -0.70
    cember
    -0.69
    soDeliveryDate
    -0.68
    terday
    -0.67
    cade
    -0.66
    POSITIVE LOGITS
     certain
    1.05
     their
    0.95
     themselves
    0.90
     employees
    0.76
     customers
    0.75
     licenses
    0.75
     subsidiaries
    0.75
     confidential
    0.73
     applicants
    0.72
     discretionary
    0.72
    Activations Density 0.444%

    No Known Activations