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

    Neuronpedia

    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. 7-RES-JB
    11. 4427
    Prev
    Next
    INDEX
    Explanations

    years or dates, particularly in the early 1990s

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific years related to events or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Edge
    -0.71
    edge
    -0.67
    hire
    -0.66
    Tu
    -0.66
     lightsaber
    -0.66
    semble
    -0.65
    holder
    -0.64
    Sensor
    -0.63
    bow
    -0.60
    videos
    -0.59
    POSITIVE LOGITS
    ĸļ
    1.01
    -'
    0.74
    ãĥŁ
    0.73
    å¹
    0.71
     census
    0.69
    achine
    0.68
    âķIJ
    0.66
    ãĥĥãĥĪ
    0.65
    ourn
    0.65
    ãĥ©ãĥ³
    0.64
    Activations Density 0.029%

    No Known Activations