INDEX

Explanations

expressions of preference

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

Έ

-0.53

स

-0.51

 benar

-0.51

↵↵↵

-0.49

端

-0.49

↵

-0.49

Tre

-0.48

glycemia

-0.47

 permission

-0.47

Parcelable

-0.47

POSITIVE LOGITS

 prefer

2.60

 preferred

2.53

preferred

2.48

 prefers

2.38

 Prefer

2.36

prefer

2.34

 Preferred

2.33

 preferring

2.18

Preferred

2.12

Prefer

2.10

Activations Density 0.076%

expressions of preference

No Comments

No Known Activations