INDEX

Explanations

locations or places such as airports, magazines, jails, zoos, and regions

oai_token-act-pair · gpt-3.5-turbo

proper nouns related to locations and organizations

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

\":

-0.75

romeda

-0.68

 fortun

-0.62

 swast

-0.60

ische

-0.57

 silence

-0.55

 multiplier

-0.55

ometric

-0.55

cients

-0.55

 wrench

-0.54

POSITIVE LOGITS

Ltd

0.91

 Limited

0.86

ļéĨĴ

0.79

istries

0.72

legate

0.64

 Services

0.63

LLC

0.63

ilaterally

0.63

ensis

0.62

chlor

0.61

Activations Density 0.486%

locations or places such as airports, magazines, jails, zoos, and regions

proper nouns related to locations and organizations

No Comments

No Known Activations