INDEX

Explanations

references to the Academy or awards related to films

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

onges

-0.64

 '\\;'

-0.62

conazole

-0.61

il

-0.61

gib

-0.60

Bil

-0.59

 Hendrix

-0.59

Bil

-0.59

rif

-0.58

uyasha

-0.57

POSITIVE LOGITS

 Academy

1.38

 academies

1.37

 academy

1.34

 ACADEMY

1.33

Academy

1.23

ValueStyle

1.13

 Academies

1.03

academy

1.02

 ―――――

0.92

ACADEM

0.91

Activations Density 0.004%

references to the Academy or awards related to films

No Comments

No Known Activations

references to the Academy or awards related to films

No Comments

No Known Activations