INDEX

Explanations

modal verbs and their negations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 medel

-0.49

UnusedPrivate

-0.48

PreInfinity

-0.47

 omkring

-0.47

 auszu

-0.45

zeera

-0.45

 einzu

-0.43

 tekem

-0.43

execSQL

-0.42

kabau

-0.42

POSITIVE LOGITS

But

0.98

但她

0.97

but

0.96

 pero

0.92

但却

0.90

但在

0.88

But

0.87

but

0.85

但这

0.83

但他

0.82

Activations Density 0.278%

modal verbs and their negations

No Comments

No Known Activations