© 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. 3-RES-JB
    11. 3315
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal matters or positions of authority

    oai_token-act-pair · gpt-3.5-turbo

    the verb "be" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     monop
    -0.78
     partName
    -0.73
     stakes
    -0.71
     nap
    -0.71
     glide
    -0.70
    ilver
    -0.68
     referen
    -0.67
    rador
    -0.67
     runaway
    -0.67
     pole
    -0.65
    POSITIVE LOGITS
    yond
    1.38
    arers
    1.12
    arer
    1.07
    cker
    1.03
    ech
    1.02
    ardless
    0.98
    ards
    0.97
    acon
    0.97
    FORE
    0.93
    ek
    0.92
    Activations Density 0.011%

    No Known Activations