INDEX

Explanations

references to individuals in senior positions or titles

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

-0.65

IMF

-0.52

 Testamento

-0.51

 imagin

-0.51

 كمان

-0.50

Билгалдахарш

-0.50

 MainAxisSize

-0.49

ctility

-0.48

DrawerToggle

-0.48

 Proclamation

-0.48

POSITIVE LOGITS

 senior

5.04

 Senior

4.63

senior

4.57

Senior

4.49

 SENIOR

4.11

SENIOR

3.91

 seniors

3.50

 Seniors

3.08

Seniors

2.98

 junior

2.81

Activations Density 0.061%

references to individuals in senior positions or titles

No Comments

No Known Activations