INDEX

Explanations

proper nouns and names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/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.15.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

adaptiveStyles

-1.07

-0.86

 Wray

-0.80

imel

-0.79

 calendriers

-0.79

 Omer

-0.78

 grun

-0.77

BeginContext

-0.75

 Esquire

-0.75

σταση

-0.74

POSITIVE LOGITS

 Gorg

0.86

 gall

0.81

 Sorg

0.80

 Bals

0.79

awtextra

0.74

 postId

0.71

 kaikk

0.70

Dz

0.69

ölf

0.69

NAZ

0.67

Activations Density 1.004%

proper nouns and names

No Comments

No Known Activations