INDEX

Explanations

relevant phrases or indicators in discussions about performance and evidence in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

MethodManager

-0.70

 الفلك

-0.61

 referrerpolicy

-0.59

WithIOException

-0.56

ukkig

-0.56

 kasarigan

-0.55

oneg

-0.55

nî

-0.54

AttributeSet

-0.54

něž

-0.53

POSITIVE LOGITS

 protoimpl

0.71

fromnode

0.64

 StatefulWidget

0.63

SuppressLint

0.59

States

0.57

 States

0.56

states

0.54

 stanu

0.54

 estados

0.54

 states

0.53

Activations Density 0.250%

relevant phrases or indicators in discussions about performance and evidence in various contexts

No Comments

No Known Activations