© 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. 7-RES-JB
    11. 16708
    Prev
    Next
    INDEX
    Explanations

    references to the establishment, creation, or development of new institutions or structures

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to the establishment or creation of new organizations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    damage
    -0.64
     wounds
    -0.61
     buttocks
    -0.61
     Errors
    -0.60
     anger
    -0.60
     humidity
    -0.59
     careless
    -0.58
     corners
    -0.58
     hog
    -0.58
    76561
    -0.58
    POSITIVE LOGITS
     modeled
    0.79
     staffed
    0.77
    achment
    0.75
    oppable
    0.74
     someday
    0.73
     incorporating
    0.71
    thood
    0.71
    rossover
    0.70
     capable
    0.69
     prototype
    0.69
    Activations Density 1.001%

    No Known Activations