INDEX

Explanations

phrases indicating personal reflections or opinions about relationships and social interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.35.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

 reportedly

-1.02

 obviously

-1.02

obviously

-0.96

 казалось

-0.96

 oczywiście

-0.94

 apparently

-0.93

seem

-0.92

 seemed

-0.92

 seemingly

-0.91

 seem

-0.91

POSITIVE LOGITS

 somehow

0.66

 algún

0.62

 وأن

0.60

 algum

0.56

 somewhere

0.56

 actually

0.50

 inderdaad

0.49

 might

0.49

 alguno

0.49

 tatsächlich

0.49

Activations Density 1.772%

phrases indicating personal reflections or opinions about relationships and social interactions

No Comments

No Known Activations