INDEX

Explanations

references to charges or fees related to legal or financial 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

 Alley

-0.84

 تانيه

-0.82

ゞ

-0.82

\"");

-0.80

>\<

-0.79

theless

-0.79

 poppies

-0.79

 للمعارف

-0.78

Viitteet

-0.78

expandindo

-0.77

POSITIVE LOGITS

 charge

2.48

 charges

2.46

charge

2.33

 Charge

2.30

Charge

2.25

 Charges

2.21

 charged

2.16

charges

2.15

 CHARGE

2.14

Charges

2.06

Activations Density 0.061%

references to charges or fees related to legal or financial contexts

No Comments

No Known Activations