© 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. 11-RES-JB
    11. 1263
    Prev
    Next
    INDEX
    Explanations

    phrases related to agreement or confirmation

    oai_token-act-pair · gpt-3.5-turbo

    words related to agreement and consensus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    brance
    -0.81
     leakage
    -0.68
    channelAvailability
    -0.68
     fragmentation
    -0.68
     exist
    -0.67
     belonging
    -0.66
     sting
    -0.66
     stocking
    -0.65
     flow
    -0.65
     inhibit
    -0.65
    POSITIVE LOGITS
    ounces
    1.22
    wrote
    1.15
    igrated
    1.11
    alks
    1.05
    aughed
    1.04
    oled
    1.04
    ighed
    1.04
    okingly
    1.04
    ushed
    1.03
    poses
    1.02
    Activations Density 0.142%

    No Known Activations