INDEX

Explanations

comparative statements beginning with "More than"

oai_token-act-pair · gpt-3.5-turbo

comparative phrases indicating quantities or measures

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

Interstitial

-0.82

EMENT

-0.73

ãĤ¼ãĤ¦ãĤ¹

-0.73

oris

-0.70

ALE

-0.69

ModLoader

-0.68

microsoft

-0.68

ALSE

-0.67

Ô

-0.67

ç·

-0.66

POSITIVE LOGITS

whelming

0.83

ground

0.67

atos

0.66

etheless

0.65

0.64

0.63

 half

0.63

0.62

Activations Density 0.049%

comparative statements beginning with "More than"

comparative phrases indicating quantities or measures

No Comments

No Known Activations