© 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. 8-RES-JB
    11. 18681
    Prev
    Next
    INDEX
    Explanations

    words related to operational activities and procedures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to operational processes and violations

    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
    theless
    -0.81
     DRAG
    -0.70
     Heller
    -0.68
    waves
    -0.67
     afore
    -0.64
    FACE
    -0.64
     MIL
    -0.64
     AMERICA
    -0.63
     rise
    -0.62
     breasts
    -0.61
    POSITIVE LOGITS
    ators
    1.82
    ative
    1.69
    atively
    1.67
    ating
    1.65
    ational
    1.64
    ations
    1.64
    ator
    1.63
    atives
    1.57
    ated
    1.50
    ates
    1.47
    Activations Density 0.086%

    No Known Activations