© 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. 4-RES-JB
    11. 22264
    Prev
    Next
    INDEX
    Explanations

    pronouns and verbs related to personal experiences and actions

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and their usage in context

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

    No Comments

    Negative Logits
     Flavoring
    -0.77
     Leader
    -0.72
    Ident
    -0.68
     Capitalism
    -0.68
    photos
    -0.63
    Lead
    -0.62
     Late
    -0.62
    Pref
    -0.61
    Leader
    -0.59
     Attribution
    -0.59
    POSITIVE LOGITS
    'll
    0.89
    'd
    0.89
     forg
    0.89
    've
    0.86
     encount
    0.84
     learnt
    0.81
    pard
    0.80
     arrived
    0.78
     seiz
    0.78
    ´
    0.77
    Activations Density 0.421%

    No Known Activations