© 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. 2429
    Prev
    Next
    INDEX
    Explanations

    terms related to physical or abstract characteristics or attributes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various properties in scientific contexts

    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
     Nadu
    -0.79
    icago
    -0.74
     Cortex
    -0.66
    atre
    -0.65
    ansen
    -0.63
     Siem
    -0.63
     Cron
    -0.61
    bone
    -0.61
    ways
    -0.61
    ACTED
    -0.61
    POSITIVE LOGITS
     properties
    0.92
    ality
    0.91
    properties
    0.85
    uation
    0.84
    Changed
    0.80
    ually
    0.80
    ious
    0.78
    iveness
    0.77
    istry
    0.76
    ally
    0.75
    Activations Density 0.045%

    No Known Activations