INDEX

Explanations

phrases indicating contrast or unexpected outcomes

oai_token-act-pair · gpt-3.5-turbo

the word "even" in various contexts

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

ffen

-0.90

aim

-0.88

isen

-0.85

rend

-0.83

Ĥİ

-0.82

idelines

-0.81

ierrez

-0.80

rition

-0.79

acker

-0.78

ayers

-0.78

POSITIVE LOGITS

 remotely

0.90

 though

0.82

 outright

0.78

handedly

0.76

 stranger

0.76

 worse

0.75

tho

0.69

 paran

0.67

 downright

0.67

monary

0.64

Activations Density 0.059%

phrases indicating contrast or unexpected outcomes

the word "even" in various contexts

No Comments

No Known Activations