INDEX

Explanations

names of awards and prizes associated with individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 autorité

-0.49

 desmotivaciones

-0.47

liceerd

-0.47

 oprot

-0.47

 autoridad

-0.47

脚注の使い方

-0.46

хьтан

-0.46

 cauſe

-0.45

ivores

-0.45

 novedades

-0.44

POSITIVE LOGITS

aro

0.44

Mn

0.44

MN

0.44

wur

0.43

Cup

0.43

Bab

0.43

 Cher

0.43

MAP

0.42

Gla

0.42

Mg

0.42

Activations Density 0.012%

names of awards and prizes associated with individuals

No Comments

No Known Activations