INDEX

Explanations

terms and phrases related to searching and locating items or information

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

Abitanti

-0.64

DataOutputStream

-0.62

المناصب

-0.59

CodeAttribute

-0.57

ieras

-0.56

termilk

-0.56

httphttps

-0.56

 Messing

-0.56

ItemBackground

-0.55

 dint

-0.55

POSITIVE LOGITS

 FIND

1.86

 Finding

1.80

find

1.79

FIND

1.78

 find

1.77

Finding

1.75

Find

1.75

finding

1.70

 Find

1.70

 finds

1.70

Activations Density 0.293%

terms and phrases related to searching and locating items or information

No Comments

No Known Activations