INDEX

Explanations

references to bone-related concepts and terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

drawal

-0.95

OrNil

-0.91

gól

-0.90

 Monfieur

-0.88



-0.86

 Vard

-0.86

Gemeinden

-0.81

Havolalar

-0.80

 ویکی‌پدی

-0.79

 pleaſure

-0.76

POSITIVE LOGITS

 Bones

1.59

 Bone

1.59

 bone

1.56

 bones

1.46

Bones

1.44

Bone

1.37

bone

1.36

bones

1.25

 skeleton

1.19

 Skeleton

1.16

Activations Density 0.296%

references to bone-related concepts and terms

No Comments

No Known Activations