INDEX

Explanations

references to violent incidents or injuries involving multiple victims

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 AssemblyCulture

-0.68

cipline

-0.65

iteness

-0.64

RIQUE

-0.62

Eko

-0.61

ſelf

-0.60

sphase

-0.60

atemala

-0.60

 uſe

-0.60

 leaſt

-0.59

POSITIVE LOGITS

 wounding

0.65

 injuries

0.56

 wounded

0.55

 wounds

0.53

contentLoaded

0.52

!*\

0.50

MethodManager

0.50

">//

0.47

 praw

0.46

 injury

0.46

Activations Density 0.197%

references to violent incidents or injuries involving multiple victims

No Comments

No Known Activations

references to violent incidents or injuries involving multiple victims

No Comments

No Known Activations