© 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. 6-RES-JB
    11. 7957
    Prev
    Next
    INDEX
    Explanations

    possessive forms indicating ownership by a person or entity

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms indicating ownership or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ij士
    -0.87
    arians
    -0.86
    Alert
    -0.85
    olkien
    -0.82
    ĪĴ
    -0.82
    Reviewer
    -0.78
    ainers
    -0.78
    obin
    -0.77
    event
    -0.77
    lehem
    -0.74
    POSITIVE LOGITS
     own
    1.25
     favourite
    1.02
     genitals
    1.01
     footsteps
    1.00
     gaze
    1.00
     favorite
    0.99
     knees
    0.97
     eyes
    0.96
     maiden
    0.96
     belongings
    0.94
    Activations Density 0.120%

    No Known Activations