© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 16431
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by sentences giving information or opinions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the pronoun "It" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     XVI
    -0.60
     xp
    -0.60
     TG
    -0.59
     Becker
    -0.59
     dozens
    -0.57
     Armageddon
    -0.56
     Chao
    -0.56
     PF
    -0.56
     UFO
    -0.56
     MIA
    -0.56
    POSITIVE LOGITS
    âĢ
    1.28
    [/
    1.28
     âĢ
    1.02
    ãĢ
    0.99
    resa
    0.96
    DonaldTrump
    0.93
    ï¸ı
    0.93
    âĢİ
    0.92
    ãĢį
    0.90
    .""
    0.89
    Activations Density 0.345%

    No Known Activations