INDEX

Explanations

terms and phrases indicating legislative or evaluative discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

нгредіє

-0.72

malink

-0.68

нгредієнти

-0.67

плек

-0.66

 Paglinawan

-0.65

 censiti

-0.62

közi

-0.61

يج

-0.60

 kids

-0.59

holtz

-0.58

POSITIVE LOGITS

#+#

0.85

CrossRef

0.75

 CreateTagHelper

0.73

مراجع

0.73

Portail

0.72

AddHtmlAttribute

0.70

 linkovi

0.69

 propOrder

0.69

 luogo

0.68

าก

0.68

Activations Density 0.476%

terms and phrases indicating legislative or evaluative discussions

No Comments

No Known Activations