INDEX

Explanations

instances of the word "bon" with varying degrees of emphasis

oai_token-act-pair · gpt-3.5-turbo

references to "bond" or variations of it

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

 Nightmares

-0.67

Å

-0.64

RPG

-0.64

antine

-0.64

Bear

-0.63

RAM

-0.63

GER

-0.62

MJ

-0.61

rama

-0.61

urred

-0.61

POSITIVE LOGITS

NetMessage

0.91

nets

0.88

xual

0.83

ial

0.83

ioxide

0.82

oning

0.78

DragonMagazine

0.77

 Rouge

0.76

omial

0.76

 partName

0.76

Activations Density 0.051%

instances of the word "bon" with varying degrees of emphasis

references to "bond" or variations of it

No Comments

No Known Activations