© 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. 6-RES-JB
    11. 11888
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by a verb related to possession or action

    oai_token-act-pair · gpt-3.5-turbo

    the use of first and third-person plural pronouns

    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
    yss
    -0.76
     Barron
    -0.74
    aughtered
    -0.72
    phans
    -0.67
    retty
    -0.66
    raints
    -0.66
    abel
    -0.65
    rets
    -0.63
    jri
    -0.61
    hatt
    -0.61
    POSITIVE LOGITS
    'd
    0.92
    'll
    0.84
    've
    0.83
     proport
    0.81
     deems
    0.77
     ourselves
    0.76
    RL
    0.76
     could
    0.76
     might
    0.75
     presently
    0.73
    Activations Density 0.155%

    No Known Activations