INDEX

Explanations

references to ranking or hierarchy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

つい

-0.55

ControllerAdvice

-0.48

-0.47

 partiellement

-0.46

↵↵

-0.46

FORCEMENT

-0.46

 polymorph

-0.46

בת

-0.45

↵

-0.45

 ingredienti

-0.45

POSITIVE LOGITS

 rank

1.21

 range

1.19

range

1.13

 ranges

1.09

 ranks

1.08

 Rank

1.06

 rangs

1.05

 RANGE

1.02

 Ranks

1.01

 Ranges

0.99

Activations Density 0.122%

references to ranking or hierarchy

No Comments

No Known Activations