INDEX

Explanations

instances of acronyms or abbreviations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

regler

-0.54

anthene

-0.52

 Burrows

-0.50

ENTI

-0.49

γρά

-0.49

 végét

-0.49

kym

-0.48

probieren

-0.48

 Esposito

-0.48

∖

-0.48

POSITIVE LOGITS

Add

1.56

Add

1.39

add

1.08

add

1.06

ADD

0.98

ADD

0.93

 ModelExpression

0.93

AddWithValue

0.91

Adding

0.87

 Adding

0.86

Activations Density 0.008%

instances of acronyms or abbreviations

No Comments

No Known Activations