INDEX

Explanations

words related to violence and harm inflicted on individuals

oai_token-act-pair · gpt-3.5-turbo

terminology related to violence and mutilation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

soDeliveryDate

-0.98

soType

-0.90

 explan

-0.84

channelAvailability

-0.80

quickShipAvailable

-0.79

ellig

-0.71

arten

-0.70

 Trader

-0.70

Role

-0.69

 latitude

-0.69

POSITIVE LOGITS

 inflicted

1.02

 wounds

0.86

bite

0.80

 Corpse

0.79

ciating

0.77

 Slaughter

0.77

 corpses

0.76

 vomiting

0.73

 havoc

0.73

 hordes

0.71

Activations Density 0.144%

words related to violence and harm inflicted on individuals

terminology related to violence and mutilation

No Comments

No Known Activations