© 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. 12599
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing opinions or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and actions related to governance or public figures

    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
     regulator
    -0.67
    vere
    -0.62
    ach
    -0.60
    icate
    -0.59
     Kills
    -0.57
    urable
    -0.57
     Malays
    -0.57
     vampire
    -0.56
     Rory
    -0.55
     [+
    -0.54
    POSITIVE LOGITS
    Enlarge
    0.87
     immediately
    0.70
     invariably
    0.67
     greeted
    0.67
     astonished
    0.65
     unsurprisingly
    0.65
    leased
    0.65
     noticed
    0.64
    ibo
    0.64
    oss
    0.63
    Activations Density 0.375%

    No Known Activations