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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8139
    Prev
    Next
    INDEX
    Explanations

    German city names that end with "dorf"

    oai_token-act-pair · gpt-3.5-turbo

    names of locations, particularly cities and places in Germany

    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
     closure
    -0.61
     paradigm
    -0.60
     voting
    -0.57
     Ind
    -0.57
     viz
    -0.57
     >>>
    -0.57
     based
    -0.55
     Scal
    -0.55
     controlling
    -0.55
     bruising
    -0.55
    POSITIVE LOGITS
    orf
    4.29
    arton
    1.42
    ruck
    1.29
    bach
    1.08
    orp
    1.05
    alus
    1.03
    sworth
    0.99
    orb
    0.97
    urst
    0.97
    orst
    0.97
    Activations Density 0.016%

    No Known Activations