© 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. 8-RES-JB
    11. 6302
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific word "Qu"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the brand name 'Quaker'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AGES
    -0.70
     heart
    -0.70
    HAEL
    -0.69
     contrast
    -0.69
    manship
    -0.67
     deed
    -0.66
     hearts
    -0.65
    fulness
    -0.64
     intensity
    -0.64
     rabbits
    -0.64
    POSITIVE LOGITS
    arantine
    1.30
    oted
    1.09
    ipped
    1.08
    inoa
    1.06
    otation
    1.05
    arie
    1.05
    artz
    1.03
    arters
    1.03
    icks
    1.02
    atern
    1.01
    Activations Density 0.018%

    No Known Activations