INDEX

Explanations

references to batch processing and related operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 gimana

-0.51

\}=

-0.48

<bos>

-0.46

 powiedział

-0.43

我说

-0.43

'])

-0.43

\}=\

-0.42

}}}

-0.42

"])

-0.42

''

-0.41

POSITIVE LOGITS

 Batch

1.23

 batch

1.14

batch

1.14

Batch

1.13

 BATCH

1.11

 batches

1.00

BATCH

0.92

batches

0.88

批

0.70

 AssemblyVersion

0.69

Activations Density 0.002%

references to batch processing and related operations

No Comments

No Known Activations