Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 16965
    Prev
    Next
    INDEX
    Explanations

    personal pronouns indicating possession, specifically "their"

    oai_token-act-pair · gpt-3.5-turbo

    the possessive pronoun "their"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BUG
    -0.73
     Unsure
    -0.71
    AAAA
    -0.71
    Wiki
    -0.69
    Wik
    -0.68
    bender
    -0.66
    AAA
    -0.65
     Thou
    -0.64
    spe
    -0.63
    peak
    -0.63
    POSITIVE LOGITS
     own
    1.46
     respective
    1.31
    selves
    1.01
     newfound
    0.99
    self
    0.92
     favourite
    0.92
     deepest
    0.91
     rightful
    0.90
     selves
    0.89
     entire
    0.88
    Activations Density 0.144%

    No Known Activations