© 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. 4-RES-JB
    11. 6908
    Prev
    Next
    INDEX
    Explanations

    personal pronouns followed by possessive pronouns

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual or subject

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

    No Comments

    Negative Logits
    Ò
    -0.79
    OTA
    -0.75
    DN
    -0.75
    PLA
    -0.72
    ����
    -0.70
    2500
    -0.70
    âī
    -0.70
    —-
    -0.67
    1200
    -0.67
    ÏĢ
    -0.67
    POSITIVE LOGITS
     inability
    0.96
     biggest
    0.91
    itage
    0.90
    ths
    0.87
     goal
    0.87
     Majesty
    0.86
     opinions
    0.85
     willingness
    0.85
    self
    0.82
     favourite
    0.82
    Activations Density 0.151%

    No Known Activations