INDEX

Explanations

expressions of concern or anxiety

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

IsMutable

-0.61

 StringTokenizer

-0.56

enderror

-0.54

 lượt

-0.54

ктан

-0.51

posób

-0.49

pendenti

-0.48

 själv

-0.48

randi

-0.48

UPAC

-0.46

POSITIVE LOGITS

 worry

3.23

 worries

3.15

 worried

3.10

 Worry

2.96

worry

2.89

 worrying

2.89

 concern

2.70

 concerns

2.54

 Concern

2.46

 Concerns

2.45

Activations Density 0.062%

expressions of concern or anxiety

No Comments

No Known Activations