© 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. 6-RES-JB
    11. 20260
    Prev
    Next
    INDEX
    Explanations

    references to the city of Munich

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Munich."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bable
    -0.80
    ever
    -0.78
    wright
    -0.77
    ordinate
    -0.77
    lear
    -0.74
    apsed
    -0.72
    bleacher
    -0.72
    ults
    -0.70
    efeated
    -0.69
    casting
    -0.69
    POSITIVE LOGITS
     Munich
    1.22
     Kern
    0.94
     Mü
    0.89
     Chancellor
    0.87
     Bav
    0.85
     Vienna
    0.81
     Wolfgang
    0.79
     Schro
    0.78
     GER
    0.77
     Herz
    0.76
    Activations Density 0.084%

    No Known Activations