© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 4762
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by an action

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    possessive pronouns indicating ownership or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    -+-+
    -0.93
    lished
    -0.86
    ellen
    -0.83
    oak
    -0.81
    alde
    -0.76
    raved
    -0.75
    llah
    -0.73
    tu
    -0.71
    oS
    -0.71
    rano
    -0.70
    POSITIVE LOGITS
     cues
    1.36
     cue
    1.22
     rightful
    1.11
     chances
    1.05
     talents
    1.03
     frustrations
    1.00
     oath
    0.96
     revenge
    0.94
     place
    0.91
     plunge
    0.88
    Activations Density 0.028%

    No Known Activations