INDEX

Explanations

proper names, specifically names with the term "Jean"

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Jean."

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

TPPStreamerBot

-0.80

ãĥ¼ãĥ³

-0.80

awar

-0.71

ramid

-0.69

earable

-0.68

 Flavoring

-0.68

Ö¼

-0.68

holders

-0.68

BIP

-0.67

meg

-0.66

POSITIVE LOGITS

ette

0.96

 Francois

0.86

 Claude

0.86

 Jean

0.84

 Jacques

0.81

 FranÃ§ois

0.80

 Baptist

0.77

 Pierre

0.76

esis

0.76

Cla

0.75

Activations Density 0.015%

proper names, specifically names with the term "Jean"

mentions of the name "Jean."

No Comments

No Known Activations