INDEX

Explanations

mentions implying holding law enforcement accountable

oai_token-act-pair · gpt-3.5-turbo

the occurrences of the word "is"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Heist

-0.69

 Spray

-0.67

 override

-0.64

isions

-0.63

 Lauder

-0.63

 Mayer

-0.62

 Tours

-0.61

 Trends

-0.60

 Include

-0.59

roups

-0.59

POSITIVE LOGITS

been

1.15

 gonna

1.02

 been

1.01

got

0.94

 gotten

0.94

 proud

0.88

 gotta

0.88

 glad

0.87

gotten

0.86

 willing

0.85

Activations Density 0.075%

mentions implying holding law enforcement accountable

the occurrences of the word "is"

No Comments

No Known Activations