© 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. 4-RES-JB
    11. 22644
    Prev
    Next
    INDEX
    Explanations

    phrases related to being oriented towards a specific focus or direction in a professional or purposeful context

    oai_token-act-pair · gpt-3.5-turbo

    terms related to different types of orientations or focus

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

    No Comments

    Negative Logits
    arthy
    -0.84
    yards
    -0.72
    flies
    -0.71
    Chance
    -0.71
    Tes
    -0.69
    ylon
    -0.69
    Chief
    -0.68
    aders
    -0.68
    avering
    -0.67
    enegger
    -0.67
    POSITIVE LOGITS
    eering
    1.07
     oriented
    0.95
     toward
    0.90
    irection
    0.89
    xual
    0.89
     towards
    0.86
    atives
    0.85
    mble
    0.82
     exha
    0.81
    ational
    0.79
    Activations Density 0.012%

    No Known Activations