© 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. 18532
    Prev
    Next
    INDEX
    Explanations

    age-related criteria in legal or official contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to age eligibility and employment status

    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
    NK
    -0.71
    sers
    -0.65
    rieg
    -0.62
     fir
    -0.61
    once
    -0.61
     farewell
    -0.60
    raq
    -0.58
    Tes
    -0.57
     impunity
    -0.57
    owitz
    -0.57
    POSITIVE LOGITS
     or
    0.82
     sponsoring
    0.78
     (>
    0.75
    restricted
    0.75
     ineligible
    0.74
     lawfully
    0.73
     eligible
    0.72
    insured
    0.70
     exempt
    0.70
     qualifies
    0.69
    Activations Density 0.710%

    No Known Activations