INDEX

Explanations

the word "that" and its variations in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

RegressionTest

-0.65

pes

-0.52

 itinéraires

-0.50

 yakin

-0.48

 msgs

-0.44

Uwaga

-0.44

<bos>

-0.43

 agonists

-0.41

 canals

-0.41

 nanop

-0.40

POSITIVE LOGITS

THAT

0.97

That

0.94

that

0.88

 That

0.86

__*/

0.86

}{@

0.84

 THAT

0.84

 nakalista

0.82

 فريبيس

0.81

liflower

0.74

Activations Density 0.202%

the word "that" and its variations in context

No Comments

No Known Activations