INDEX

Explanations

terms related to defense and loyalty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

makeText

-0.66

TintMode

-0.59

 TAMBIÉN

-0.59

 إل

-0.56

igshid

-0.55

heiser

-0.52

 hoạch

-0.52

inaire

-0.51

 AspNetCore

-0.51

audiovisuel

-0.50

POSITIVE LOGITS

 Defend

1.07

 defend

1.03

 defends

0.98

 defended

0.95

 defending

0.93

 défendre

0.82

 défend

0.79

 DEFEND

0.74

 indisponible

0.72

 avenge

0.72

Activations Density 0.289%

terms related to defense and loyalty

No Comments

No Known Activations