INDEX

Explanations

numbers

oai_token-act-pair · gpt-3.5-turbo

references to numerical values, particularly the words "four" and "five."

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

UGE

-0.74

Hub

-0.73

geist

-0.72

LER

-0.72

ARP

-0.70

ULE

-0.69

TM

-0.68

HY

-0.68

 Rica

-0.67

asta

-0.66

POSITIVE LOGITS

teenth

1.74

teen

1.65

 hundred

1.34

fold

1.30

eenth

1.23

een

1.22

aciously

1.16

 thousand

1.10

acious

1.08

uously

1.01

Activations Density 0.122%

numbers

references to numerical values, particularly the words "four" and "five."

No Comments

No Known Activations