© 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. 3-RES-JB
    11. 20411
    Prev
    Next
    INDEX
    Explanations

    mentions of names or terms related to specific institutions or individuals, particularly those including "Bir"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names and entities related to organizations and individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imately
    -0.61
    ULT
    -0.60
    owder
    -0.59
    EMBER
    -0.59
     Partnership
    -0.59
    OPLE
    -0.58
    ĵĺ
    -0.58
    ortium
    -0.58
    eur
    -0.58
     Tune
    -0.57
    POSITIVE LOGITS
    git
    1.02
    mingham
    1.01
     Bir
    0.95
    thing
    0.95
    ging
    0.90
    keley
    0.89
    gement
    0.88
    gers
    0.87
    combe
    0.86
    neys
    0.86
    Activations Density 0.010%

    No Known Activations