INDEX

Explanations

consistent phrases referring to institutions or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

httphttps

-0.63

setVerticalGroup

-0.57

complexContent

-0.56

 fuma

-0.54

RegressionTest

-0.53

참고

-0.51

IsContent

-0.49

CreateMap

-0.49

Hentet

-0.49

antMatchers

-0.48

POSITIVE LOGITS

󠁢

0.82

olesale

0.79

ENEFITS

0.77

 مُعرِّف

0.76

SCAPE

0.75

ercises

0.74

 RSITY

0.71

arası

0.70

ICIAL

0.69

ICAGO

0.68

Activations Density 0.110%

consistent phrases referring to institutions or organizations

No Comments

No Known Activations