© 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. 18638
    Prev
    Next
    INDEX
    Explanations

    technical terms related to online platforms and activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various forms of activities and events

    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
     Helpful
    -0.81
    EStream
    -0.77
     Parenthood
    -0.74
    Ô
    -0.74
     Kinnikuman
    -0.72
    IRED
    -0.67
    hap
    -0.66
    urate
    -0.65
     Dow
    -0.63
    ricular
    -0.63
    POSITIVE LOGITS
     series
    0.81
     program
    0.79
     badge
    0.78
     facility
    0.77
     scheme
    0.77
     kit
    0.75
     capsule
    0.75
    ilogy
    0.75
     division
    0.72
     bloc
    0.72
    Activations Density 0.366%

    No Known Activations