INDEX

Explanations

proper nouns, specifically related to names of people and places

oai_token-act-pair · gpt-3.5-turbo

names of people and locations

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

abase

-0.85

ufact

-0.83

swick

-0.80

umbered

-0.75

 defect

-0.66

ruary

-0.65

Tea

-0.64

 slightest

-0.63

shire

-0.61

displayText

-0.61

POSITIVE LOGITS

hiba

0.92

Ïģ

0.78

hei

0.75

jin

0.75

nova

0.73

unic

0.69

kat

0.68

idis

0.67

ensen

0.67

âĿ

0.64

Activations Density 0.493%

proper nouns, specifically related to names of people and places

names of people and locations

No Comments

No Known Activations