© 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. 21933
    Prev
    Next
    INDEX
    Explanations

    phrases related to rules and consequences

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to responsibility and accountability in various contexts

    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
    roud
    -0.60
    essors
    -0.60
     closures
    -0.57
     respectively
    -0.55
    etsk
    -0.54
     Countries
    -0.53
    JB
    -0.53
    angular
    -0.53
    osure
    -0.52
    ernels
    -0.51
    POSITIVE LOGITS
     himself
    1.61
     his
    1.54
    his
    1.32
     herself
    1.24
     HIS
    1.19
    His
    1.15
     Himself
    1.15
     he
    1.04
     His
    1.02
     her
    1.02
    Activations Density 0.677%

    No Known Activations