INDEX

Explanations

phrases indicating well-being or something being in a good condition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Schaefer

-0.93

ობ

-0.74

dci

-0.69

ᾶ

-0.67

 Titans

-0.67

 récla

-0.66

 Schäfer

-0.66

 DiCaprio

-0.66

TableBody

-0.66

 McCann

-0.66

POSITIVE LOGITS

 well

1.99

 Well

1.86

 WELL

1.85

Well

1.82

well

1.80

 wells

1.61

WELL

1.56

 Wells

1.44

Wells

1.42

 Welles

1.35

Activations Density 0.072%

phrases indicating well-being or something being in a good condition

No Comments

No Known Activations