© 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. 6-RES-JB
    11. 20606
    Prev
    Next
    INDEX
    Explanations

    adjectives related to intentionality

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with intentionality or premeditated actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĪĴ
    -0.82
    houses
    -0.80
    stals
    -0.80
    models
    -0.78
    zona
    -0.78
    ington
    -0.74
    region
    -0.73
    ophon
    -0.72
    azine
    -0.72
    mark
    -0.71
    POSITIVE LOGITS
     violation
    0.96
     manslaughter
    0.91
     intentional
    0.91
     effort
    0.91
    ities
    0.90
     wrongdoing
    0.89
    aneous
    0.87
     omission
    0.85
     action
    0.83
     infringement
    0.83
    Activations Density 0.073%

    No Known Activations