© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 18507
    Prev
    Next
    INDEX
    Explanations

    phrases that reference a unit or entity as a whole

    oai_token-act-pair · gpt-3.5-turbo

    references to collective groups or the concept of "whole" in relation to a nation or society

    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
    andon
    -0.89
    ATURES
    -0.69
    yang
    -0.66
    CHAPTER
    -0.64
    etz
    -0.64
    uden
    -0.64
    Joy
    -0.63
    indal
    -0.63
    orange
    -0.62
    abel
    -0.62
    POSITIVE LOGITS
     result
    1.47
     consequence
    1.26
     whole
    1.24
     standalone
    0.92
     matter
    0.92
     predictor
    0.90
     percentage
    0.87
     cohesive
    0.87
     multiplier
    0.84
     deterrent
    0.84
    Activations Density 0.096%

    No Known Activations