INDEX

Explanations

terms related to enemies and their characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

-0.57

 Birk

-0.56

lactin

-0.56

Gid

-0.53

 correndo

-0.52

lccn

-0.52

-0.51

POSITIVE LOGITS

 Enemy

1.68

 enemy

1.68

 enemies

1.58

 Enemies

1.55

Enemy

1.44

enemy

1.42

 foes

1.41

 opponents

1.38

enemies

1.32

 opponent

1.30

Activations Density 0.109%

terms related to enemies and their characteristics

No Comments

No Known Activations