© 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 EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 7051
    Prev
    Next
    INDEX
    Explanations

    terms related to specific subjects or concepts like "winner", "faith", "language gene", "invisible technologies", "standard", and "middle class"

    oai_token-act-pair · gpt-3.5-turbo

    specific keywords or phrases related to classification and categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     «
    -0.86
     �
    -0.81
     ãĢĮ
    -0.80
    ãĢĮ
    -0.73
     §§
    -0.71
     ''
    -0.66
     ().
    -0.64
     (@
    -0.63
    -0.63
    âĶĢ
    -0.61
    POSITIVE LOGITS
    "?
    1.65
    "
    1.64
    ")
    1.60
    "!
    1.56
    ",
    1.56
    "-
    1.51
    ").
    1.50
    "),
    1.49
    %"
    1.46
    "—
    1.43
    Activations Density 0.305%

    No Known Activations