© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 20170
    Prev
    Next
    INDEX
    Explanations

    words related to inclusivity and promoting a united community

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to inclusivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LAN
    -0.74
    fly
    -0.73
    nexus
    -0.72
    nit
    -0.70
    thin
    -0.69
    raz
    -0.69
    flies
    -0.68
    Mesh
    -0.68
    folder
    -0.67
     Bees
    -0.67
    POSITIVE LOGITS
     inclusive
    1.33
    entric
    0.97
     minded
    0.90
    clusive
    0.70
     frank
    0.68
    clus
    0.68
     welcoming
    0.67
     spaces
    0.66
    rification
    0.66
     tolerant
    0.65
    Activations Density 0.005%

    No Known Activations