© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 414
    Prev
    Next
    INDEX
    Explanations

    activations related to a specific news or organization abbreviation

    oai_token-act-pair · gpt-3.5-turbo

    acronyms containing "RC"

    oai_token-act-pair · gpt-4-turbo

    mentions of the abbreviation "RC" related to various organizations

    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
     ç¥ŀ
    -0.85
    ãĥ³ãĤ¸
    -0.83
    ãĥ¼ãĥĨ
    -0.75
    ãĥĦ
    -0.73
    ãĥĻ
    -0.72
    ãĤ¤
    -0.72
     Dolphin
    -0.71
    quickShipAvailable
    -0.69
     Huff
    -0.67
    ãĤ¤ãĥĪ
    -0.67
    POSITIVE LOGITS
    RC
    1.28
    MP
    0.93
    OUP
    0.82
    trl
    0.81
    RD
    0.81
    RS
    0.80
    ouble
    0.78
    ategory
    0.77
    Ps
    0.75
    ombat
    0.75
    Activations Density 0.012%

    No Known Activations