INDEX

Explanations

references to 'PR' followed by numeric values or specific terms related to public relations or medical contexts

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

Negative Logits

 xanth

-0.73

 Goff

-0.72

Портал

-0.69

 lọc

-0.68

pieler

-0.68

 Gorg

-0.67

ائه

-0.66

ագրություններ

-0.66

 Gould

-0.65

gasse

-0.64

POSITIVE LOGITS

PR

1.63

pr

1.57

pr

1.57

PR

1.55

Pr

1.40

Pr

1.38

pri

1.29

pri

1.26

Pri

1.22

Prat

1.12

Activations Density 0.091%

references to 'PR' followed by numeric values or specific terms related to public relations or medical contexts

No Known Activations