© 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. 867
    Prev
    Next
    INDEX
    Explanations

    words related to transparency and regulation in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to transparency and regulatory compliance

    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
    mania
    -0.84
    renheit
    -0.72
     Bie
    -0.70
     Cooking
    -0.70
    akeru
    -0.70
    moil
    -0.69
    Hit
    -0.69
     MISS
    -0.68
     Tyrann
    -0.68
     Melt
    -0.68
    POSITIVE LOGITS
     accountability
    1.61
     transparency
    1.54
     accountable
    1.41
     safeguards
    1.40
     transparent
    1.39
     oversight
    1.36
     equitable
    1.30
     impartial
    1.24
     fairness
    1.21
     interoper
    1.20
    Activations Density 0.412%

    No Known Activations