© 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. 8-RES-JB
    11. 7056
    Prev
    Next
    INDEX
    Explanations

    terms related to personal qualities and evaluations such as worth, status, ability, capabilities, limitations, toughness, skill, reputation, character, potential, and strength

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to personal value and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    annon
    -0.71
    tein
    -0.66
     Manufact
    -0.65
    vae
    -0.64
    ongyang
    -0.59
    urb
    -0.58
    bris
    -0.58
     Federation
    -0.58
     Administ
    -0.58
     Airl
    -0.57
    POSITIVE LOGITS
    iness
    0.90
    é¾įåĸļ士
    0.83
     vis
    0.83
    abilities
    0.82
    worthiness
    0.81
     predicament
    0.80
     selves
    0.79
    iest
    0.79
     abilities
    0.77
    lessness
    0.76
    Activations Density 0.339%

    No Known Activations