INDEX

Explanations

roles related to leadership or directorship positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Jank

-0.78

romyalgia

-0.70

ꜱ

-0.69

 "','

-0.67

<h6>

-0.65

 Schwab

-0.64

ikkert

-0.64

issner

-0.64

lipop

-0.63

Jennie

-0.62

POSITIVE LOGITS

 directors

1.34

 Directors

1.24

Directors

1.13

 director

1.07

 DIRECTOR

1.03

directors

1.02

director

1.01

Dir

1.01

 Director

0.96

 Diri

0.96

Activations Density 0.073%

roles related to leadership or directorship positions

No Comments

No Known Activations