INDEX

Explanations

phrases indicating job titles or organizational affiliations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

if

-0.51

个

-0.50

ci

-0.48

cin

-0.48

ist

-0.47

ous

-0.47

se

-0.46

eng

-0.46

int

-0.46

ம்ப

-0.45

POSITIVE LOGITS

 CreateTagHelper

1.12

 فريبيس

0.96

OOTDTY

0.78

Попис

0.76

 estekak

0.75

fitrión

0.74

 Roskov

0.73

ronique

0.73

abetes

0.72

yntaxException

0.72

Activations Density 0.539%

phrases indicating job titles or organizational affiliations

No Comments

No Known Activations