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. 6-RES-JB
    6. 1827
    Prev
    Next
    INDEX
    Explanations

    pronouns 'they' and 'she' referring to multiple entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "they."

    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
     Cumber
    -0.73
     Globe
    -0.70
     Dome
    -0.70
     Eleven
    -0.69
     Vine
    -0.65
     Eps
    -0.65
     Wol
    -0.64
     Kinn
    -0.61
    terness
    -0.60
    amia
    -0.60
    POSITIVE LOGITS
    're
    1.12
    've
    1.10
    'd
    1.08
    selves
    0.98
    'll
    0.95
     encount
    0.83
    self
    0.82
    stanbul
    0.82
     numbered
    0.79
     could
    0.77
    Activations Density 0.097%

    No Known Activations