INDEX

Explanations

phrases that indicate pointing out or emphasizing specific information or arguments

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

ⓘ

-0.58

JsonInclude

-0.52

ServiceModel

-0.51

 Sentiment

-0.48

まで

-0.48

bootstrapcdn

-0.47

elemField

-0.46

PreInfinity

-0.45

XmlEnum

-0.44

wahati

-0.43

POSITIVE LOGITS

 CreateTagHelper

1.03

 fingers

0.95

脚注の使い方

0.86

abestanden

0.86

 finger

0.83

fingers

0.77

 doigt

0.76

Fingers

0.72

 accusing

0.71

finger

0.71

Activations Density 0.081%

phrases that indicate pointing out or emphasizing specific information or arguments

No Comments

No Known Activations