© 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. 9-RES-JB
    11. 10122
    Prev
    Next
    INDEX
    Explanations

    pronouns or words related to personal actions or attributes

    oai_token-act-pair · gpt-3.5-turbo

    pronouns that indicate personal or collective identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    church
    -0.70
    bender
    -0.65
    aston
    -0.61
     Elim
    -0.59
     Eleven
    -0.58
     Nationwide
    -0.58
    luster
    -0.57
    whel
    -0.57
    quartered
    -0.56
     Dres
    -0.55
    POSITIVE LOGITS
    've
    0.94
     perceive
    0.89
     learnt
    0.88
    're
    0.88
     ate
    0.87
     aspire
    0.82
     learned
    0.82
     meant
    0.81
     saw
    0.80
     accomplished
    0.80
    Activations Density 0.136%

    No Known Activations