© 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. 0-RES-JB
    11. 11865
    Prev
    Next
    INDEX
    Explanations

    adjectives ending in '-ous' or '-ious'

    oai_token-act-pair · gpt-3.5-turbo

    words related to dangerous or precarious situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     decay
    -0.67
     decor
    -0.65
     Piet
    -0.64
     estab
    -0.64
     radios
    -0.63
     decon
    -0.62
     monop
    -0.62
     lith
    -0.60
     wards
    -0.59
     redes
    -0.59
    POSITIVE LOGITS
    ificant
    1.92
    itous
    1.88
    asive
    1.85
    uable
    1.85
    asonable
    1.81
    itious
    1.79
    icable
    1.77
    urious
    1.72
    uitous
    1.64
    amous
    1.64
    Activations Density 0.057%

    No Known Activations