© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 13908
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals holding political positions

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations and their official titles or roles

    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
    Defense
    -0.95
    avored
    -0.94
     honoring
    -0.91
     favored
    -0.89
    defense
    -0.87
    rollment
    -0.87
    Arizona
    -0.87
    bors
    -0.85
     honor
    -0.85
     Bundy
    -0.84
    POSITIVE LOGITS
     £
    1.43
     centre
    1.39
     realise
    1.38
     recognise
    1.37
    £
    1.33
    colour
    1.31
     Labour
    1.30
     Scotland
    1.29
     aluminium
    1.27
     centres
    1.26
    Activations Density 1.381%

    No Known Activations