© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 23065
    Prev
    Next
    INDEX
    Explanations

    words related to technology and implementations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to uncertainty or doubt about effectiveness

    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
    irming
    -0.82
    irmed
    -0.72
    STON
    -0.65
    FINE
    -0.64
    Sav
    -0.64
    soType
    -0.64
     remission
    -0.62
    venge
    -0.62
    rontal
    -0.62
    Cool
    -0.62
    POSITIVE LOGITS
     lacks
    1.33
     lacked
    1.29
     couldn
    1.17
     suffers
    1.14
     fails
    1.12
     cannot
    1.12
     struggled
    1.08
     lack
    1.08
     struggles
    1.05
     failed
    1.01
    Activations Density 0.468%

    No Known Activations