INDEX

Explanations

references to bears and bear-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

lrrrr

-0.77

 Pelop

-0.69

Rau

-0.67

 Schur

-0.64

UTERS

-0.64

 Carthag

-0.63

 Vlas

-0.63

ghed

-0.62

Rau

-0.62

 Lapp

-0.61

POSITIVE LOGITS

 Bears

1.10

 Bear

1.04

 BEAR

1.01

 bears

0.98

Bear

0.98

 bear

0.94

 bearing

0.91

Bears

0.90

 Bearing

0.89

BEAR

0.87

Activations Density 0.419%

references to bears and bear-related terms

No Comments

No Known Activations