INDEX

Explanations

words related to warranties and legal disclaimers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

FormTagHelper

-0.79

 kaarangay

-0.77

 kasarigan

-0.77

 betweenstory

-0.74

 beginnetje

-0.70

 Мексичка

-0.66

 himo

-0.65

titleMargin

-0.63

 nonUne

-0.60

 '\\;'

-0.60

POSITIVE LOGITS

PREFERRED

4.21

Preferred

1.49

 Preferred

1.47

 preferred

1.46

preferred

1.37

REFERRED

1.00

setPreferred

0.95

 preferable

0.87

 prefer

0.83

Preferences

0.81

Activations Density 0.007%

words related to warranties and legal disclaimers

No Comments

No Known Activations