INDEX

Explanations

references to scientific authors or contributors in a formal context

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

"]();

-0.56

 glyphicon

-0.56

ό

-0.56

 appre

-0.54

Mox

-0.54

âm

-0.54

 fevere

-0.53

 διά

-0.53

 pointe

-0.53

 reafon

-0.53

POSITIVE LOGITS

al

1.43

TintMode

0.78

 alia

0.77

hibli

0.75

Al

0.74

 Lordships

0.73

ArrowToggle

0.73

 CURIAM

0.72

 AspNetCore

0.71

AsUp

0.71

Activations Density 0.061%

references to scientific authors or contributors in a formal context

No Comments

No Known Activations