INDEX

Explanations

numerical values and their representations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

']],

-0.70

 autorytatywna

-0.69

iddhar

-0.64

 Reif

-0.63

eſt

-0.61

czaj

-0.61

mantel

-0.61

 refor

-0.61

'],

-0.61

égal

-0.60

POSITIVE LOGITS

1.70

０

0.92

০

0.89

۰

0.88

pellier

0.84

०

0.80

۰۰

0.71

Literals

0.69

𝟎

0.69

눠

0.68

Activations Density 0.438%

numerical values and their representations

No Comments

No Known Activations