© 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. 11959
    Prev
    Next
    INDEX
    Explanations

    personal pronouns used in first person singular

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the pronoun "I"

    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
    ienne
    -0.64
     Rapids
    -0.63
    Ħ¢
    -0.63
     Papers
    -0.61
     Butter
    -0.60
    inus
    -0.59
     Sales
    -0.58
     Bezos
    -0.57
     Vie
    -0.57
     Alexandria
    -0.57
    POSITIVE LOGITS
    'm
    1.46
    've
    1.30
     guess
    1.17
    'll
    1.12
     think
    1.03
    'd
    1.02
     suppose
    1.01
    nex
    0.97
     believe
    0.96
     gotta
    0.93
    Activations Density 0.247%

    No Known Activations