INDEX

Explanations

references to directors or individuals in leadership positions

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

脚注の使い方

-0.77

WindowConstants

-0.65

Datuak

-0.64

 يتيمه

-0.64

 Soldier

-0.63

UnusedPrivate

-0.61

новниш

-0.61

 bouch

-0.61

namentales

-0.61

kloped

-0.61

POSITIVE LOGITS

 director

3.85

 Director

3.71

Director

3.52

director

3.35

 DIRECTOR

3.23

 directors

3.14

 Directors

2.88

DIRECTOR

2.74

Directors

2.63

directors

2.60

Activations Density 0.064%

references to directors or individuals in leadership positions

No Comments

No Known Activations