© 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. 3-RES-JB
    11. 12137
    Prev
    Next
    INDEX
    Explanations

    references to the city of Berlin

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Berlin

    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
    BOOK
    -0.87
    lihood
    -0.80
    merce
    -0.77
    orses
    -0.75
    DonaldTrump
    -0.74
    tml
    -0.73
    said
    -0.73
    à¤
    -0.71
    avez
    -0.71
    ````
    -0.70
    POSITIVE LOGITS
    mouth
    0.89
     Berlin
    0.89
     Chancellor
    0.87
    shire
    0.85
    furt
    0.82
    enburg
    0.81
     Blitz
    0.79
    er
    0.78
     Pact
    0.77
     Wall
    0.77
    Activations Density 0.007%

    No Known Activations