INDEX

Explanations

expressions of affirmation or agreement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

]--;

-0.81

WriteBarrier

-0.80

NUMX

-0.79

 '\\;'

-0.78

aarrggbb

-0.78

".

-0.75

 TestBed

-0.75

pozdrawiam

-0.73

),

-0.71

POSITIVE LOGITS

 Well

2.04

Well

2.02

 WELL

1.25

well

1.21

WELL

1.11

Welp

1.03

 well

0.90

 Ну

0.85

 Okay

0.83

 Welles

0.83

Activations Density 0.044%

expressions of affirmation or agreement

No Comments

No Known Activations