INDEX

Explanations

terms related to warnings and alerts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 aDecoder

-0.67

 FetchType

-0.65

 للاسماء

-0.59

databind

-0.56

lodash

-0.56

 NavController

-0.55

 daraus

-0.55

uría

-0.55

yntaxException

-0.53

íncia

-0.53

POSITIVE LOGITS

 alerts

1.21

 warning

1.17

 alert

1.17

 Alerts

1.13

astify

1.12

 warnings

1.10

 warn

1.08

 Warnings

1.06

Alerts

1.01

 Warn

1.00

Activations Density 0.131%

terms related to warnings and alerts

No Comments

No Known Activations