INDEX

Explanations

references to ranking, competition, and performance in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

-0.65

or

-0.63

-0.62

↵↵

-0.56

-0.52

and

-0.51

-0.48

<eos>

-0.46

POSITIVE LOGITS

 Majefty

1.35

ſelf

1.29

 Monfieur

1.26

 myſelf

1.18

 doubtnut

1.16

 ſeveral

1.14

 ―――――

1.12

 themſelves

1.11

 Jefus

1.11

 Anſ

1.10

Activations Density 0.348%

references to ranking, competition, and performance in various contexts

No Comments

No Known Activations