INDEX

Explanations

references to the word "the" 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 @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 فريبيس

-0.67

})));

-0.65

))));

-0.58

 forma

-0.57

internalType

-0.55

XMLSchema

-0.55

))).

-0.53

Enllaces

-0.52

 NUKAT

-0.51



-0.51

POSITIVE LOGITS

 meantime

0.98

 words

0.88

 الحره

0.78

 past

0.72

SequentialGroup

0.72

 meanwhile

0.70

 next

0.66

end

0.65

 immortal

0.64

 spirit

0.63

Activations Density 0.274%

references to the word "the" in various contexts

No Comments

No Known Activations