© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 15652
    Prev
    Next
    INDEX
    Explanations

    words related to technology devices and functions

    oai_token-act-pair · gpt-3.5-turbo

    terms that relate to technical specifications and components in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    姫
    -0.82
    ousy
    -0.78
    otropic
    -0.71
    romy
    -0.67
    å¸
    -0.64
    Saharan
    -0.63
    etime
    -0.62
    ãĤ¢ãĥ«
    -0.61
    solete
    -0.59
    ESCO
    -0.59
    POSITIVE LOGITS
     itself
    1.23
     portion
    0.85
     continuum
    0.81
    forts
    0.79
     quo
    0.78
    ariat
    0.77
    eers
    0.77
     themselves
    0.76
    liest
    0.76
    osphere
    0.75
    Activations Density 0.655%

    No Known Activations