© 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. 7001
    Prev
    Next
    INDEX
    Explanations

    instances where the possessive pronoun "its" is used

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the pronoun "its."

    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
    rette
    -0.74
     Thib
    -0.70
    GB
    -0.67
    stad
    -0.66
    eering
    -0.65
    Gallery
    -0.64
    ij士
    -0.64
    shed
    -0.63
     Timberwolves
    -0.63
     Rockies
    -0.63
    POSITIVE LOGITS
     own
    1.20
    ELF
    1.19
    self
    0.96
    elf
    0.88
     respective
    0.87
    asca
    0.86
     predecessor
    0.84
     newest
    0.81
     predecessors
    0.81
     namesake
    0.79
    Activations Density 0.100%

    No Known Activations