INDEX

Explanations

phrases related to violent acts, such as "slaughter."

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "slaughter" and its variations in context

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

BuyableInstoreAndOnline

-0.75

DCS

-0.72

ioxide

-0.68

 fortun

-0.68

âĵĺ

-0.63

verage

-0.61

ency

-0.61

aucas

-0.60

annis

-0.60

rouse

-0.58

POSITIVE LOGITS

houses

1.16

 Slaughter

1.14

house

0.98

ificial

0.88

 slaughter

0.87

hide

0.85

hammer

0.85

ãĥ¼ãĤ¯

0.81

birds

0.81

 slaughtered

0.81

Activations Density 0.028%

phrases related to violent acts, such as "slaughter."

mentions of the word "slaughter" and its variations in context

No Comments

No Known Activations