© 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. 11592
    Prev
    Next
    INDEX
    Explanations

    adjectives related to negative emotions and medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various states of emotional or physical distress and vulnerability

    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
    Downloadha
    -0.91
     sidx
    -0.79
    76561
    -0.78
    ickr
    -0.73
    ioxide
    -0.68
    abwe
    -0.66
    ATT
    -0.64
    arty
    -0.61
    aeda
    -0.61
    è£ħ
    -0.60
    POSITIVE LOGITS
    ness
    3.27
    nesses
    2.67
    NESS
    2.12
    ity
    1.49
    liness
    1.48
    ening
    1.45
    ly
    1.44
    itude
    1.35
    ened
    1.24
    cies
    1.20
    Activations Density 0.142%

    No Known Activations