© 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. 7-RES-JB
    6. 7244
    Prev
    Next
    INDEX
    Explanations

    names of different groups or organizations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hyde
    -0.76
     adul
    -0.75
     spoil
    -0.71
     tantal
    -0.71
     fetch
    -0.70
     temptation
    -0.70
    washer
    -0.68
    reci
    -0.67
     inh
    -0.67
     curv
    -0.67
    POSITIVE LOGITS
    affiliated
    1.14
     chaired
    1.09
     disbanded
    1.04
    roups
    0.98
     convened
    0.98
    members
    0.97
    PAC
    0.97
     headquartered
    0.96
     affiliated
    0.95
    organized
    0.94
    Activations Density 0.514%

    No Known Activations