© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 23967
    Prev
    Next
    INDEX
    Explanations

    phrases indicating separation or isolation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating separation or isolation from a larger group or system

    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
    ivot
    -0.74
     enthusi
    -0.74
    Corn
    -0.70
    CVE
    -0.70
     proble
    -0.67
     inhibitor
    -0.67
    KC
    -0.65
    seek
    -0.63
    raq
    -0.63
     toget
    -0.63
    POSITIVE LOGITS
     afar
    0.94
     whence
    0.82
     thence
    0.72
     others
    0.68
     Ble
    0.63
     herd
    0.61
     Ones
    0.60
     what
    0.59
    ainers
    0.59
     reality
    0.58
    Activations Density 0.075%

    No Known Activations