INDEX

Explanations

phrases related to queries or discoveries about items, relationships, or conditions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 <=",

-0.71

TProtocol

-0.64

thenReturn

-0.64

zzleHttp

-0.64

帖最后由

-0.63

itinéraire

-0.63

twimg

-0.61

 leaſt

-0.60

mobileqq

-0.58

 שוליים

-0.57

POSITIVE LOGITS

finding

0.73

 Find

0.73

find

0.71

FIND

0.71

 FIND

0.71

 find

0.71

Find

0.70

 Finding

0.69

 found

0.69

 finding

0.68

Activations Density 0.486%

phrases related to queries or discoveries about items, relationships, or conditions

No Comments

No Known Activations