© 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. 10-RES-JB
    11. 3049
    Prev
    Next
    INDEX
    Explanations

    terms related to physical attributes and qualities, particularly focusing on health and wellness

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to various aspects of health, wellbeing, and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ
    -0.68
    itialized
    -0.67
    oso
    -0.64
    arnaev
    -0.64
    aughed
    -0.63
    redited
    -0.60
    estern
    -0.60
     Azerbai
    -0.58
    lass
    -0.58
    sonian
    -0.58
    POSITIVE LOGITS
     itself
    1.18
     versus
    1.02
     matters
    1.01
     alone
    0.89
     upkeep
    0.87
     vs
    0.84
    uality
    0.82
     issues
    0.82
     anymore
    0.81
     themselves
    0.81
    Activations Density 0.390%

    No Known Activations