INDEX

Explanations

referenced limits or constraints in a mathematical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

-0.67

-0.65

the

-0.62

↵↵

-0.58

in

-0.56

to

-0.54

-0.52

for

-0.52

and

-0.50

POSITIVE LOGITS

 BOUND

1.03

 Bounds

1.02

 tartalomajánló

0.97

uxxxx

0.92

 bounds

0.92

 estimés

0.91

initializeApp

0.87

İstinadlar

0.86

 auffi

0.85

bounds

0.85

Activations Density 0.148%

referenced limits or constraints in a mathematical context

No Comments

No Known Activations