© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4859
    Prev
    Next
    INDEX
    Explanations

    words related to industry and innovation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to industry and innovation

    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
    theless
    -1.01
    unin
    -0.88
    rooms
    -0.85
    ÃŃa
    -0.84
    illac
    -0.84
    etheless
    -0.83
    ¶ħ
    -0.81
    ength
    -0.77
    aver
    -0.77
    pter
    -0.77
    POSITIVE LOGITS
     Cooperation
    0.97
     Investor
    0.97
     Solutions
    0.96
     Security
    0.95
     Identification
    0.94
     Group
    0.94
     Promotion
    0.94
     Partnership
    0.92
     Development
    0.91
     Consult
    0.90
    Activations Density 0.055%

    No Known Activations