INDEX

Explanations

elements of question and answer interactions, especially in a legal context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 فريبيس

-0.77

клопе

-0.73

Geplaatst

-0.70

tagHelper

-0.63

FormTagHelper

-0.62

 protoimpl

-0.61

MENAFN

-0.61

 CreateTagHelper

-0.61

 VizieR

-0.59

Liefs

-0.58

POSITIVE LOGITS

 asked

0.84

 perguntou

0.76

 asks

0.73

 inquired

0.72

 asking

0.71

asked

0.71

 pregunt

0.71

 enquired

0.70

 inquiring

0.70

 bertanya

0.69

Activations Density 0.674%

elements of question and answer interactions, especially in a legal context

No Comments

No Known Activations