INDEX

Explanations

references to the car manufacturer "BMW" with varying model numbers and contexts

oai_token-act-pair · gpt-3.5-turbo

references to the BMW automotive brand

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

ional

-0.89

arters

-0.71

pid

-0.71

lement

-0.69

aways

-0.68

brate

-0.68

tainment

-0.67

mond

-0.67

 Lauder

-0.66

Las

-0.66

POSITIVE LOGITS

sonian

0.79

ueller

0.79

OTHER

0.78

olitan

0.75

oru

0.74

imil

0.72

BM

0.71

OGR

0.71

ASS

0.71

 Mayhem

0.69

Activations Density 0.014%

references to the car manufacturer "BMW" with varying model numbers and contexts

references to the BMW automotive brand

No Comments

No Known Activations