INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

the occurrences of the word "usted" and related proper nouns

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

ured

-0.90

actic

-0.82

antha

-0.79

azon

-0.75

otropic

-0.74

Ī

-0.74

omorphic

-0.73

ory

-0.72

emic

-0.69

otin

-0.68

POSITIVE LOGITS

mine

0.85

DERR

0.73

PDATE

0.72

ARDS

0.72

ried

0.70

 Giuliani

0.70

hower

0.67

ARD

0.66

 golf

0.65

iated

0.63

Activations Density 0.052%

proper nouns

the occurrences of the word "usted" and related proper nouns

No Comments

No Known Activations