INDEX

Explanations

the word "that" and its variants used in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

PHA

-0.59

vements

-0.59

vc

-0.58

 Rhymes

-0.58

Bip

-0.57

 angio

-0.56

MV

-0.56

consult

-0.56

 Magi

-0.56

AMR

-0.55

POSITIVE LOGITS

THAT

1.64

that

1.57

 That

1.54

 THAT

1.51

That

1.51

 that

1.37

thats

0.98

Thats

0.97

this

0.94

脚注の使い方

0.93

Activations Density 0.203%

the word "that" and its variants used in various contexts

No Comments

No Known Activations