© 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. 20796
    Prev
    Next
    INDEX
    Explanations

    phrases related to computer systems or programming

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific system or organizational structure

    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
    fet
    -0.77
    ishable
    -0.75
    ghan
    -0.75
    tein
    -0.69
    assador
    -0.66
    hyde
    -0.65
    quer
    -0.64
    20439
    -0.64
     earnest
    -0.64
    uel
    -0.64
    POSITIVE LOGITS
    atics
    0.95
    atic
    0.84
     System
    0.81
     Shock
    0.81
     Procedures
    0.76
    wide
    0.75
     Components
    0.74
     Reaction
    0.73
     Integrity
    0.72
     Dynamics
    0.71
    Activations Density 0.016%

    No Known Activations