© 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. 3-RES-JB
    11. 23212
    Prev
    Next
    INDEX
    Explanations

    verbs or verbs in passive voice that relate to things being propelled, motivated, or guided by specific factors or entities

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to causation or motivation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iannopoulos
    -0.87
    iao
    -0.78
    aido
    -0.76
    achu
    -0.75
     Flavoring
    -0.75
    itu
    -0.74
    oho
    -0.71
    çĦ
    -0.69
     Murdoch
    -0.68
    eon
    -0.68
    POSITIVE LOGITS
     driven
    0.97
     driving
    0.90
    driving
    0.88
    vable
    0.81
    driven
    0.81
    bys
    0.75
     drives
    0.72
    ousel
    0.72
     Dri
    0.70
    whe
    0.69
    Activations Density 0.020%

    No Known Activations