INDEX

Explanations

phrases indicating comparisons or similarities

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

"as" followed by a pronoun or auxiliary verb

np_acts-logits-general · gemini-2.0-flash

as we

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

TemporalType

-0.52

antaranya

-0.51

/?

-0.50

IFS

-0.48

 Ако

-0.47

<^

-0.46

 Implications

-0.46

OOTDTY

-0.46

vieja

-0.45

bertas

-0.45

POSITIVE LOGITS

 there

1.14

 opposed

1.04

 most

0.86

 InputDecoration

0.84

 oppose

0.80

it

0.78

 long

0.73

you

0.72

 mentioned

0.71

there

0.71

Activations Density 0.124%

phrases indicating comparisons or similarities

"as" followed by a pronoun or auxiliary verb

as we

No Known Activations