© 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. 23723
    Prev
    Next
    INDEX
    Explanations

    phrases involving the concept of control or authority

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to possession or control

    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
    wcs
    -0.79
    isms
    -0.75
    stuff
    -0.70
    together
    -0.68
    pring
    -0.67
    iations
    -0.67
    Join
    -0.67
    Reply
    -0.65
    rise
    -0.65
    ilver
    -0.65
    POSITIVE LOGITS
     smugglers
    0.82
     traffickers
    0.81
     unsuspecting
    0.76
     inexperienced
    0.75
     superiors
    0.74
     beh
    0.73
    hung
    0.73
     extremists
    0.72
     whoever
    0.72
     regulators
    0.69
    Activations Density 0.153%

    No Known Activations