© 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. 11-RES-JB
    11. 22326
    Prev
    Next
    INDEX
    Explanations

    personal pronouns, particularly the pronoun "he", or descriptions involving personal experiences

    oai_token-act-pair · gpt-3.5-turbo

    references to a particular person or character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    include
    -0.63
     Globe
    -0.60
     expire
    -0.60
     Are
    -0.55
     Include
    -0.55
     Header
    -0.55
     Dominion
    -0.55
     guiActiveUnfocused
    -0.54
     AAA
    -0.54
    regulation
    -0.53
    POSITIVE LOGITS
     thinks
    1.26
     himself
    1.22
     remembers
    1.22
    'd
    1.19
     believes
    1.17
     knows
    1.14
     sees
    1.09
     prefers
    1.08
     knew
    1.08
     considers
    1.06
    Activations Density 0.297%

    No Known Activations