© 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. 7-RES-JB
    11. 2829
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or behaviors that involve interaction or participation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "engage" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esa
    -0.65
    orah
    -0.65
    arily
    -0.63
    loo
    -0.62
    ennis
    -0.62
     ported
    -0.61
     Mexicans
    -0.61
    edu
    -0.60
    ario
    -0.60
    bowl
    -0.60
    POSITIVE LOGITS
     meaningful
    0.85
     conversation
    0.80
     vigorous
    0.79
     continual
    0.77
     mutual
    0.77
     risky
    0.75
    ordinate
    0.74
     constructive
    0.73
     constant
    0.72
     hostilities
    0.71
    Activations Density 0.048%

    No Known Activations