INDEX

Explanations

phrases that denote instances or cases in a report or analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

OrBuilder

-0.63

xtures

-0.63

GETHER

-0.63

 disponibilités

-0.61

 ISNI

-0.60

ENI

-0.60

ترنت

-0.60

vestres

-0.60

########.

-0.59

backdrop

-0.58

POSITIVE LOGITS

 cases

1.36

 case

1.19

 Cases

1.07

 casos

1.02

Cases

0.96

 geval

0.95

 kasus

0.94

 caso

0.92

case

0.92

cases

0.91

Activations Density 0.381%

phrases that denote instances or cases in a report or analysis

No Comments

No Known Activations