© 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. 0-RES-JB
    11. 15681
    Prev
    Next
    INDEX
    Explanations

    mentions of branches in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to organizational or government branches

    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
    owicz
    -0.70
    ographics
    -0.66
     rive
    -0.65
    aze
    -0.64
     Herman
    -0.63
     selfies
    -0.61
    onom
    -0.60
     Cancel
    -0.60
     Enough
    -0.60
     unforgettable
    -0.60
    POSITIVE LOGITS
     branch
    4.05
     branches
    2.82
     Branch
    2.58
     branching
    1.64
     trunk
    1.30
    ranch
    1.25
     tree
    1.22
     strand
    1.11
     mainline
    1.05
     subsidiary
    1.03
    Activations Density 0.005%

    No Known Activations