INDEX

Explanations

actions related to data processing and manipulation

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

ValueStyle

-0.77

LookAnd

-0.71

 propOrder

-0.67

ſy

-0.58

LayoutInflater

-0.56

 gainera

-0.54

PageFactory

-0.54

 ſtre

-0.54

 juſ

-0.53

isSuccessful

-0.51

POSITIVE LOGITS

twimg

0.52

TemporalType

0.51

iedo

0.51

BeanUtils

0.50

íqu

0.49

المكان

0.49

 fär

0.48

Enllaces

0.47

UrlResolution

0.47

 dann

0.47

Activations Density 0.517%

actions related to data processing and manipulation

No Comments

No Known Activations