© 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. 17096
    Prev
    Next
    INDEX
    Explanations

    educational institutions such as schools, colleges, and bases

    oai_token-act-pair · gpt-3.5-turbo

    names of educational institutions and medical facilities

    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
    alys
    -0.75
    20439
    -0.69
    taboola
    -0.68
    genre
    -0.67
    oven
    -0.67
    colour
    -0.66
    margin
    -0.65
     invari
    -0.64
    relations
    -0.63
    film
    -0.62
    POSITIVE LOGITS
     Hospital
    0.88
     Ltd
    0.88
     Campus
    0.81
     Complex
    0.79
     Inc
    0.78
     Authority
    0.74
     Senior
    0.74
     District
    0.74
     LLC
    0.74
     Headquarters
    0.74
    Activations Density 0.127%

    No Known Activations