INDEX

Explanations

expressions indicating reasoning or actions related to awareness and decision-making

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

parsedMessage

-0.90

httphttps

-0.74

 SUDOC

-0.73

WebElementEntity

-0.70

alnız

-0.69

 ویکی‌پدیا

-0.68

 newBuilder

-0.66

 thither

-0.64

setVerticalGroup

-0.63

ագրություններ

-0.63

POSITIVE LOGITS

 what

3.92

what

3.12

What

2.59

 What

2.54

 WHAT

2.41

WHAT

2.22

 whats

1.89

 hvad

1.79

whats

1.78

hva

1.76

Activations Density 0.891%

expressions indicating reasoning or actions related to awareness and decision-making

No Comments

No Known Activations