© 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. 22615
    Prev
    Next
    INDEX
    Explanations

    complex and intricate concepts or systems

    oai_token-act-pair · gpt-3.5-turbo

    terms related to complexity and intricate subjects

    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
    usha
    -0.75
    §
    -0.70
    inburgh
    -0.69
    OIL
    -0.68
    ä¸Ĭ
    -0.68
    ablishment
    -0.65
    ï¸
    -0.65
    Naz
    -0.65
    monton
    -0.65
     Volunteers
    -0.64
    POSITIVE LOGITS
    ioned
    1.25
    ions
    0.96
     logistical
    0.93
     mathematical
    0.91
     equations
    0.90
     maze
    0.90
    mble
    0.89
     calculations
    0.88
     maths
    0.85
     dynamics
    0.85
    Activations Density 0.090%

    No Known Activations