INDEX

Explanations

choice-related phrases and 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 @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

sient

-0.41

udra

-0.40

webElement

-0.40

Enabled

-0.39

 Kary

-0.39

ابس

-0.37

ssan

-0.37

างเกง

-0.37

ulous

-0.37

addImage

-0.37

POSITIVE LOGITS

 preferring

1.88

 prefer

1.77

 preference

1.77

 prefers

1.73

 Prefer

1.70

prefer

1.69

 preferred

1.59

 предпоч

1.54

 Preference

1.54

 préf

1.53

Activations Density 0.537%

choice-related phrases and expressions of preference

No Comments

No Known Activations