INDEX

Explanations

phrases indicating various relational or dependent clauses starting with "so."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

shafen

-0.54

semi

-0.49

-0.47

becue

-0.47

 semi

-0.47

lossians

-0.47

Bob

-0.46

 Ader

-0.45

Scalars

-0.45

 Grand

-0.44

POSITIVE LOGITS

 propOrder

1.02

ImageContext

0.76

bootstrapcdn

0.74

帖最后由

0.72

المشاركات

0.72

########.

0.69

httphttps

0.69

SequentialGroup

0.64

TagHelper

0.63

 EconPapers

0.63

Activations Density 0.138%

phrases indicating various relational or dependent clauses starting with "so."

No Comments

No Known Activations