INDEX

Explanations

references to accidents, injuries, and associated medical conditions or treatments

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 EconPapers

-0.56

Архівовано

-0.56

NegativeButton

-0.52

település

-0.50

liyor

-0.49

Skocz

-0.47

Hochspringen

-0.47

 capito

-0.47

apimachinery

-0.47

++)

-0.46

POSITIVE LOGITS

 while

2.88

while

2.63

 WHILE

2.32

 whilst

2.31

 mientras

2.28

 enquanto

2.26

 mentre

2.24

While

2.19

 While

2.16

WHILE

2.03

Activations Density 0.850%

references to accidents, injuries, and associated medical conditions or treatments

No Comments

No Known Activations