INDEX

Explanations

instances of the word "shows" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AndEndTag

-0.57

ñata

-0.56

 νε

-0.49

mith

-0.48

uerto

-0.48

čiai

-0.47

 intest

-0.47

 screen

-0.46

gu

-0.46

hä

-0.46

POSITIVE LOGITS

 shows

1.81

shows

1.68

 Shows

1.67

Shows

1.65

 SHOWS

1.51

hows

1.34

 illustrates

0.91

 indicates

0.91

Manbalar

0.89

 zeigt

0.88

Activations Density 0.173%

instances of the word "shows" and its variations in different contexts

No Comments

No Known Activations