© 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. 7561
    Prev
    Next
    INDEX
    Explanations

    phrases related to hard work, dedication, perseverance, and sacrifice

    oai_token-act-pair · gpt-3.5-turbo

    themes related to hard work and dedication

    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
    ãĥĺãĥ©
    -0.81
     Vend
    -0.76
    ONSORED
    -0.69
    Haunted
    -0.69
    Ń·
    -0.65
    IX
    -0.65
    ãĥķãĤ©
    -0.64
     fallout
    -0.64
     Victims
    -0.63
     Bans
    -0.63
    POSITIVE LOGITS
    smanship
    1.02
    fulness
    0.90
    itiveness
    0.87
    idious
    0.87
    FUL
    0.86
     effort
    0.84
    abl
    0.81
    ability
    0.76
    ful
    0.76
    manship
    0.74
    Activations Density 0.315%

    No Known Activations