© 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. 9-RES-JB
    11. 3550
    Prev
    Next
    INDEX
    Explanations

    German words or terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Der" and its variations, likely in reference to German-language media or articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The token "Der"

    Explanation Uploaded by User
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zzi
    -0.67
    hearted
    -0.67
     Intermediate
    -0.66
     Dragonbound
    -0.65
    eous
    -0.65
    hetti
    -0.64
    eur
    -0.64
     Holmes
    -0.60
    heartedly
    -0.60
    orsi
    -0.59
    POSITIVE LOGITS
    isively
    1.07
    bys
    1.06
    mal
    1.05
    iving
    1.04
    ivation
    0.95
    isive
    0.95
    ricks
    0.94
    bil
    0.94
    anged
    0.92
    rick
    0.90
    Activations Density 0.032%

    No Known Activations