INDEX

Explanations

references to popularity and recognition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

LookAnd

-0.61

 الرياضيه

-0.58

 OMITBAD

-0.56

ymce

-0.56

nehå

-0.54

śli

-0.50

CharStream

-0.49

findpost

-0.46

Latest

-0.46

 strdup

-0.45

POSITIVE LOGITS

 loved

1.48

 admired

1.46

 appreciated

1.44

 respected

1.40

 adored

1.39

 liked

1.35

 sought

1.30

 popular

1.29

 recognized

1.27

 revered

1.27

Activations Density 0.349%

references to popularity and recognition

No Comments

No Known Activations