© 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. 9-RES-JB
    11. 15999
    Prev
    Next
    INDEX
    Explanations

    words related to the element "gan" within them

    oai_token-act-pair · gpt-3.5-turbo

    words related to "gan" and its variations, indicating a focus on specific terminology or concepts in a particular field

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OTUS
    -0.75
    ĺħ
    -0.73
    ĵĺ
    -0.72
    eneg
    -0.67
    ension
    -0.66
    ensional
    -0.65
    estinal
    -0.65
    hovah
    -0.64
    ractive
    -0.62
    avorite
    -0.60
    POSITIVE LOGITS
    cia
    1.07
    ously
    1.03
    esis
    1.00
    icity
    0.94
    omics
    0.93
    ous
    0.93
    osity
    0.91
    etically
    0.88
    als
    0.87
    etic
    0.85
    Activations Density 0.083%

    No Known Activations