© 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
    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. 22301
    Prev
    Next
    INDEX
    Explanations

    government agencies and regulatory bodies

    oai_token-act-pair · gpt-3.5-turbo

    mentions of regulatory organizations and agencies related to public health and safety

    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
    lan
    -0.82
    lang
    -0.74
    å¦
    -0.73
    kell
    -0.70
    loe
    -0.67
    ician
    -0.66
    boxes
    -0.65
    matter
    -0.65
    byn
    -0.65
    iques
    -0.63
    POSITIVE LOGITS
     (
    0.93
     ("
    0.88
    Enlarge
    0.82
     (.
    0.78
     headquartered
    0.78
     ()
    0.74
     Task
    0.73
     Commission
    0.70
     [(
    0.70
     approves
    0.70
    Activations Density 0.137%

    No Known Activations