© 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. 8-RES-JB
    11. 22286
    Prev
    Next
    INDEX
    Explanations

    press releases mentioning contacts and organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to business or organizational roles and official contact information

    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
     deduction
    -0.90
     toss
    -0.83
     deductions
    -0.83
     ensl
    -0.79
     rigged
    -0.79
     trope
    -0.77
     deduct
    -0.76
     spawning
    -0.75
     chop
    -0.74
     twists
    -0.73
    POSITIVE LOGITS
    Office
    1.23
    Department
    1.11
    Contact
    1.10
    Copyright
    1.02
    Website
    1.00
    Development
    0.98
    International
    0.98
    Address
    0.94
    Services
    0.91
    Contribut
    0.90
    Activations Density 0.208%

    No Known Activations