INDEX

Explanations

phrases indicating universality or generalization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

onio

-0.44

ствия

-0.42

Storyboard

-0.42

主意

-0.41

mologie

-0.41

ahal

-0.41

low

-0.41

an

-0.40

|>

-0.39

Ref

-0.39

POSITIVE LOGITS

 every

1.99

every

1.99

Every

1.94

 Every

1.93

Chaque

1.82

 Chaque

1.80

EVERY

1.74

Each

1.73

 Each

1.72

 each

1.72

Activations Density 0.408%

phrases indicating universality or generalization

No Comments

No Known Activations