INDEX

Explanations

warnings or alerts about potential risks or issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

uxxxx

-0.91

 مرئيه

-0.81

 FetchType

-0.73

хьтан

-0.73

lodash

-0.68

KommentareTeilen

-0.68

="@+

-0.68

 NavController

-0.65

 للمعارف

-0.65

 بيها

-0.64

POSITIVE LOGITS

 warning

1.79

 warn

1.77

 warnings

1.69

 Warning

1.60

 warns

1.57

 warned

1.55

 Warnings

1.52

warning

1.49

 Warn

1.45

warn

1.45

Activations Density 0.041%

warnings or alerts about potential risks or issues

No Comments

No Known Activations