© 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. 8-RES-JB
    11. 17567
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to oneself or themselves

    oai_token-act-pair · gpt-3.5-turbo

    reflexive pronouns and phrases related to self-reference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onal
    -0.64
     Mub
    -0.63
    cru
    -0.61
    iens
    -0.60
    aptic
    -0.60
    microsoft
    -0.60
    itty
    -0.59
    grade
    -0.59
     Alger
    -0.58
    emis
    -0.57
    POSITIVE LOGITS
    é¾įåĸļ士
    0.75
    ãĥĥãĥĪ
    0.74
    ãĥķ
    0.73
    ãĤĭ
    0.71
    ãģ¾
    0.70
    ãģı
    0.69
    è»
    0.68
    çīĪ
    0.67
    åĤ
    0.66
    ãĥĹ
    0.65
    Activations Density 0.042%

    No Known Activations