© 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. 17205
    Prev
    Next
    INDEX
    Explanations

    mentions of creating or building something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the concept of personal ownership and creation

    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
    anwhile
    -0.81
     Mub
    -0.76
    antle
    -0.68
    obar
    -0.67
     Bullets
    -0.64
     Antar
    -0.64
    hesda
    -0.63
    wy
    -0.63
    itement
    -0.63
    hovah
    -0.63
    POSITIVE LOGITS
     custom
    0.87
     homegrown
    0.84
     version
    0.81
     personal
    0.79
     customized
    0.79
     selves
    0.76
     unique
    0.76
     creations
    0.73
     accord
    0.72
     personalized
    0.71
    Activations Density 0.035%

    No Known Activations