INDEX

Explanations

words related to death and violence

oai_token-act-pair · gpt-3.5-turbo

terms related to death and casualties in violent contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 ellipt

-0.78

 Wonderland

-0.78

 Cary

-0.76

 Horizons

-0.73

 Collider

-0.73

imum

-0.72

 Cascade

-0.72

 Gemini

-0.72

ellar

-0.71

inventoryQuantity

-0.70

POSITIVE LOGITS

 Rohingya

1.05

 civilians

1.02

 Afghans

1.00

 killings

0.98

 Palestinians

0.98

soever

0.98

 atrocities

0.98

 Syrians

0.94

 bombing

0.94

 Palestinian

0.93

Activations Density 0.152%

words related to death and violence

terms related to death and casualties in violent contexts

No Known Activations