INDEX

Explanations

phrases indicating causation or conditions

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

preceding a relative clause

np_acts-logits-general · gemini-2.0-flash

which the

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 prochaines

-0.78

 ongles

-0.56

 autre

-0.55

 ouvertes

-0.54

 coppia

-0.54

 âmes

-0.54

 coisa

-0.53

 rêves

-0.51

 larmes

-0.50

 côtés

-0.50

POSITIVE LOGITS

 there

1.02

)";

1.01

 individuals

1.00

)");

0.98

ividual

0.97

 individual

0.97

hematical

0.90

")"

0.90

the

0.87

etheless

0.86

Activations Density 1.118%

phrases indicating causation or conditions

preceding a relative clause

which the

No Comments

No Known Activations