Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 12053
    Prev
    Next
    INDEX
    Explanations

    quotes and phrases from various sources

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    20439
    -0.81
    è¦ļéĨĴ
    -0.74
    imet
    -0.73
    "},"
    -0.73
    rowth
    -0.72
    iband
    -0.71
    sbm
    -0.70
    ãĤ¼ãĤ¦ãĤ¹
    -0.69
    alysed
    -0.68
    MpServer
    -0.68
    POSITIVE LOGITS
     irony
    1.17
     kidding
    1.16
    HAHAHAHA
    1.03
     pity
    1.01
     ironic
    1.00
     shame
    0.97
     laughable
    0.97
    Huh
    0.96
    Seriously
    0.92
     amusing
    0.92
    Activations Density 0.479%

    No Known Activations