© 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. 14066
    Prev
    Next
    INDEX
    Explanations

    the name "Bern" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific name, primarily "Bern."

    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
     partName
    -0.76
    mson
    -0.73
    NetMessage
    -0.71
    WARE
    -0.69
     clipboard
    -0.67
     SPORTS
    -0.67
    intendent
    -0.66
    «ĺ
    -0.66
    ------------------------------------------------
    -0.66
    ãĥīãĥ©
    -0.64
    POSITIVE LOGITS
    anke
    1.43
    aby
    0.99
    hard
    0.99
    hal
    0.93
    hart
    0.92
    ayan
    0.92
    ardo
    0.90
    etta
    0.90
    stein
    0.86
    ibal
    0.83
    Activations Density 0.023%

    No Known Activations