© 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. 4-RES-JB
    11. 7069
    Prev
    Next
    INDEX
    Explanations

    phrases related to strength, reliability, and effectiveness

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "robust" and its variations, indicating a focus on strength or effectiveness in various contexts

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

    No Comments

    Negative Logits
     clicked
    -0.68
    Station
    -0.67
    OPA
    -0.65
    frey
    -0.65
     Station
    -0.63
    ioxide
    -0.62
     Suc
    -0.61
    Tube
    -0.60
    pper
    -0.60
     Khe
    -0.60
    POSITIVE LOGITS
    ness
    1.08
    ly
    1.08
    nesses
    1.01
    ively
    1.00
    ament
    0.89
     characterization
    0.85
    mble
    0.85
    ity
    0.84
    iveness
    0.84
    itude
    0.83
    Activations Density 0.014%

    No Known Activations