INDEX

Explanations

occurrences of the word "write" in various forms and contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

帖最后由

-0.94

LookAnd

-0.84

unhofer

-0.82

 resourceCulture

-0.81

*)&

-0.79

ConstraintMaker

-0.79

NameInMap

-0.79

 defStyleAttr

-0.78

awtextra

-0.77

antd

-0.76

POSITIVE LOGITS

 writing

2.12

 write

1.99

 Writing

1.85

write

1.85

 wrote

1.77

 writes

1.77

Writing

1.76

 WRITING

1.76

writing

1.75

Write

1.72

Activations Density 0.101%

occurrences of the word "write" in various forms and contexts

No Comments

No Known Activations