© 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. 1396
    Prev
    Next
    INDEX
    Explanations

    identifiers of different operating systems, specifically "OS 9."

    oai_token-act-pair · gpt-3.5-turbo

    references to operating systems

    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
    ãĥ¬
    -0.71
    aneous
    -0.70
    ouses
    -0.70
    ãĥ©ãĥ³
    -0.69
    starter
    -0.69
    ildo
    -0.68
     Hurricanes
    -0.68
    ritz
    -0.67
    ãĤ¡
    -0.67
    aneously
    -0.66
    POSITIVE LOGITS
    DAQ
    1.00
    OS
    0.92
     ANGEL
    0.86
    omal
    0.84
    leep
    0.83
    Gi
    0.81
    OM
    0.81
    MIC
    0.76
    chwitz
    0.75
    RM
    0.75
    Activations Density 0.007%

    No Known Activations