INDEX

Explanations

repetitive uses of the word "so."

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

 vertes

-0.79

μία

-0.77

 Breton

-0.75

 hond

-0.74

 Artemis

-0.73

 Catania

-0.73

 Ancona

-0.73

 Winfrey

-0.73

 剪影

-0.72

Artemis

-0.72

POSITIVE LOGITS

so

1.95

So

1.63

So

1.59

so

1.56

SO

1.49

SO

1.19

 sooooo

1.08

 sooo

1.08

Sooo

1.07

Så

1.02

Activations Density 0.113%

repetitive uses of the word "so."

No Comments

No Known Activations