© 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. 3-RES-JB
    11. 15290
    Prev
    Next
    INDEX
    Explanations

    terms related to Earth's atmospheric layers

    oai_token-act-pair · gpt-3.5-turbo

    words related to various "spheres," such as atmosphere, biosphere, and others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abet
    -0.80
    IVERS
    -0.79
    taboola
    -0.71
    utters
    -0.67
    Mur
    -0.67
    angan
    -0.66
    arov
    -0.66
    mediate
    -0.65
    urga
    -0.64
    payer
    -0.64
    POSITIVE LOGITS
    osphere
    1.13
    cules
    0.79
    ï¸
    0.77
    phrine
    0.71
    icz
    0.70
    lihood
    0.70
    lette
    0.69
    ursday
    0.69
    zers
    0.68
    urs
    0.67
    Activations Density 0.018%

    No Known Activations