INDEX

Explanations

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

oai_token-act-pair · gpt-3.5-turbo

the repetition of the word "ten" in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 DRAG

-0.70

 Indust

-0.68

Downloadha

-0.66

 jerk

-0.66

ramid

-0.64

igslist

-0.62

hammad

-0.60

 Bind

-0.60

 Tonight

-0.57

HY

-0.57

POSITIVE LOGITS

aciously

1.38

acious

1.31

acity

1.26

uous

1.19

ured

1.17

fold

1.12

 thousand

1.11

uously

1.07

ieth

1.02

eenth

1.01

Activations Density 0.018%

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

the repetition of the word "ten" in various contexts

No Comments

No Known Activations