INDEX

Explanations

indicators of disparities or differences in data comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 تضيفلها

-0.61

 negeri

-0.51

énario

-0.47

mybatisplus

-0.47

 existência

-0.46

Gra

-0.45

mstyle

-0.45

egz

-0.43

office

-0.43

']='

-0.43

POSITIVE LOGITS

المناصب

0.94

[::-

0.77

 GenerationType

0.74

دانشنامهٔ

0.73

$_"

0.72

 timing

0.69

 Partagez

0.69

medel

0.68

 PMID

0.68

 fhew

0.67

Activations Density 0.353%

indicators of disparities or differences in data comparisons

No Comments

No Known Activations