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

    Neuronpedia

    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. 11-RES-JB
    11. 9438
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by relationships with others or statements relayed from others

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and references to individuals' opinions and contributions

    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
     Skydragon
    -0.82
     guiActiveUnfocused
    -0.70
    amazon
    -0.68
    animate
    -0.68
    amed
    -0.67
    uve
    -0.66
    vest
    -0.65
    hound
    -0.64
    gat
    -0.63
    enged
    -0.63
    POSITIVE LOGITS
     thoughts
    1.61
     impressions
    1.38
     own
    1.16
     Thoughts
    1.13
     views
    1.12
     reflections
    1.11
     reactions
    1.11
     opinions
    1.08
     insights
    1.07
     findings
    1.06
    Activations Density 0.144%

    No Known Activations