INDEX

Explanations

references to military conflicts or wars

oai_token-act-pair · gpt-3.5-turbo

references to wars and conflict

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

AUT

-0.74

 GOODMAN

-0.72

displayText

-0.69

FORMATION

-0.65

 confir

-0.64

OGR

-0.60

AAAA

-0.60

UCT

-0.59

Asset

-0.59

EMOTE

-0.59

POSITIVE LOGITS

 wars

1.16

lords

1.08

riors

0.96

bucks

0.96

hips

0.90

 Wars

0.87

lord

0.84

quit

0.84

 battles

0.83

 waged

0.83

Activations Density 0.007%

references to military conflicts or wars

references to wars and conflict

No Known Activations