INDEX

Explanations

words related to negative consequences or adverse effects

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate causation or harmful effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Technique

-0.73

ramid

-0.68

 Niet

-0.67

 skelet

-0.65

halla

-0.65

aeper

-0.65

 motto

-0.64

atu

-0.63

ian

-0.63

stra

-0.61

POSITIVE LOGITS

 havoc

1.12

 cele

0.93

 irre

0.85

ãĥĨãĤ£

0.84

 mayhem

0.81

 trouble

0.81

 headaches

0.80

parable

0.79

 unnecessary

0.74

hift

0.74

Activations Density 0.043%

words related to negative consequences or adverse effects

phrases that indicate causation or harmful effects

No Comments

No Known Activations