© 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 EvalsExportsinterp-engineNEWAPI 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. 5152
    Prev
    Next
    INDEX
    Explanations

    phrases indicating personal relationships

    oai_token-act-pair · gpt-3.5-turbo

    references to friendships or relationships with individuals

    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
    ItemImage
    -0.65
    essen
    -0.60
    aceous
    -0.60
    NESS
    -0.59
     assumption
    -0.58
     evaluations
    -0.58
     FANT
    -0.58
     inability
    -0.58
     Presence
    -0.58
     ];
    -0.57
    POSITIVE LOGITS
     hers
    1.15
     ours
    1.12
     yours
    1.02
     sorts
    1.00
     theirs
    0.98
     mine
    0.91
    ammad
    0.72
     course
    0.71
    irlf
    0.69
    hire
    0.66
    Activations Density 0.102%

    No Known Activations