© 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. 2-RES-JB
    11. 9249
    Prev
    Next
    INDEX
    Explanations

    references to the name "Mir"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of 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 @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OPLE
    -0.78
    ļéĨĴ
    -0.73
    YC
    -0.72
    enegger
    -0.71
    chnology
    -0.69
    CAST
    -0.69
    ocobo
    -0.69
    ggies
    -0.69
    OTAL
    -0.67
    ANY
    -0.67
    POSITIVE LOGITS
    rors
    1.15
    acles
    1.12
    rored
    1.04
    ror
    0.92
    abella
    0.89
    ial
    0.86
    acle
    0.86
    riages
    0.85
     Abram
    0.83
    abel
    0.81
    Activations Density 0.007%

    No Known Activations