© 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. 2-RES-JB
    11. 17069
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'stopped,' particularly when it is in the context of a physical action or event

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "stopped" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ighth
    -0.82
    alty
    -0.79
    eve
    -0.78
    inen
    -0.77
    bold
    -0.76
    hold
    -0.75
    MAT
    -0.71
    ally
    -0.70
    ivities
    -0.68
    eur
    -0.68
    POSITIVE LOGITS
    cffffcc
    0.77
    ĸļ
    0.76
    kered
    0.74
     abruptly
    0.73
    00200000
    0.72
     halted
    0.72
     hesitate
    0.69
     aback
    0.68
     blinking
    0.68
    CLASSIFIED
    0.67
    Activations Density 0.053%

    No Known Activations