INDEX

Explanations

frequent mentions of the word "lots"

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

 cref

-0.60

fap

-0.59

 patties

-0.54

io

-0.50

Jah

-0.49

 tout

-0.49

inchilla

-0.49

ք

-0.49

theit

-0.48

út

-0.48

POSITIVE LOGITS

 lots

1.47

Lots

1.44

 Lots

1.40

 LOTS

1.16

lots

1.12

 myſelf

0.78

ConstraintMaker

0.78

BufferException

0.78

 loads

0.76

^(@)

0.75

Activations Density 0.035%

frequent mentions of the word "lots"

No Comments

No Known Activations