© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 4273
    Prev
    Next
    INDEX
    Explanations

    words related to processing, storing, or managing information

    oai_token-act-pair · gpt-3.5-turbo

    words and concepts related to environmental interactions or biological processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Accountability
    -0.73
     Freedom
    -0.71
     Integrity
    -0.70
     Equality
    -0.66
     Consortium
    -0.65
     Coalition
    -0.64
     Enterprise
    -0.62
     Directorate
    -0.61
     Disclosure
    -0.61
     Entity
    -0.61
    POSITIVE LOGITS
    ar
    1.00
    emark
    0.99
    alled
    0.97
    ament
    0.95
    nel
    0.95
    el
    0.94
    agog
    0.93
    aned
    0.93
    aram
    0.93
    ctor
    0.91
    Activations Density 0.410%

    No Known Activations