© 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. 0-RES-JB
    11. 8191
    Prev
    Next
    INDEX
    Explanations

    references to the software company Adobe

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Adobe and its software products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hern
    -0.80
     superst
    -0.76
    unts
    -0.64
     lev
    -0.63
     punishment
    -0.63
    secret
    -0.62
     duty
    -0.61
    odies
    -0.61
    nat
    -0.60
    gang
    -0.60
    POSITIVE LOGITS
     Adobe
    3.96
    adobe
    1.94
     Photoshop
    1.92
     Cisco
    1.38
     Mozilla
    1.36
    Microsoft
    1.32
     Dropbox
    1.29
     Ubisoft
    1.27
     Microsoft
    1.25
    microsoft
    1.23
    Activations Density 0.017%

    No Known Activations