INDEX

Explanations

expressions of uncertainty or questioning

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

خابات

-0.57

YGON

-0.57

mals

-0.55

)}

-0.55

 Malam

-0.53

gyz

-0.53

}{*}{

-0.53

_('

-0.53

("}");

-0.52

 ivelany

-0.52

POSITIVE LOGITS

 تضيفلها

0.81

tagHelperRunner

0.78

WireFormatLite

0.73

UnusedPrivate

0.71

مراجع

0.71

Diweddarwch

0.68

WriteTagHelper

0.64

曖昧さ回避

0.64

 متعلقه

0.64

 whatsoever

0.64

Activations Density 0.545%

expressions of uncertainty or questioning

No Comments

No Known Activations