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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16980
    Prev
    Next
    INDEX
    Explanations

    technical terms and specifications related to devices or equipment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to adjustable airflow and insulation products

    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
    Politics
    -0.69
     injust
    -0.64
    arians
    -0.63
     Vaugh
    -0.63
    cember
    -0.63
     speeches
    -0.58
    Ire
    -0.58
    uary
    -0.58
    ocracy
    -0.58
    prison
    -0.58
    POSITIVE LOGITS
     adjustable
    1.10
     modular
    0.95
     Specifications
    0.95
     removable
    0.94
     adapter
    0.94
     compact
    0.91
     coil
    0.91
     reversible
    0.90
     sensor
    0.90
     PCB
    0.88
    Activations Density 0.774%

    No Known Activations