INDEX

Explanations

repetitive underscore characters and the word "new."

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

IMPORTED

-1.20

httphttps

-0.90

 handleMessage

-0.86

ſelves

-0.84

GeneratedMessage

-0.82

 Majefty

-0.77

$_"

-0.74

 resourceCulture

-0.74

makeText

-0.74

 myſelf

-0.73

POSITIVE LOGITS

kaan

0.54

alibaba

0.54

 AssemblyTitle

0.53

 judíos

0.51

yip

0.48

เภ

0.47

茉

0.47

روج

0.47

0.46

 iParam

0.46

Activations Density 0.043%

repetitive underscore characters and the word "new."

No Comments

No Known Activations