INDEX

Explanations

references to groups of people or collective terms used throughout the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

sidemargin

-0.65

 dàng

-0.57

 @"";

-0.55

бл

-0.54

Gtk

-0.53

økt

-0.52

참고

-0.52

主に

-0.50

figer

-0.49

 Pingback

-0.49

POSITIVE LOGITS

 everyone

3.90

everyone

3.74

Everyone

3.61

 Everyone

3.59

 everybody

3.37

 Everybody

3.24

everybody

3.23

Everybody

3.14

 EVERYONE

3.07

 iedereen

2.31

Activations Density 0.079%

references to groups of people or collective terms used throughout the text

No Comments

No Known Activations