© 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. 1-RES-JB
    11. 20230
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Mir"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Mir" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    YC
    -0.69
    ocobo
    -0.68
    ANY
    -0.67
    iculty
    -0.67
    restling
    -0.67
    ļéĨĴ
    -0.65
    ential
    -0.62
    etition
    -0.62
    cific
    -0.62
    shapeshifter
    -0.61
    POSITIVE LOGITS
    acles
    1.06
    rors
    1.06
    rored
    0.92
     Mir
    0.87
    ror
    0.83
    ial
    0.82
    acle
    0.80
    imir
    0.78
    abella
    0.78
    abel
    0.76
    Activations Density 0.008%

    No Known Activations