INDEX

Explanations

references to a specific location or event named "Camp"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Camp" along with segment delimiters

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

lihood

-0.91

 magnification

-0.78

 regress

-0.75

insured

-0.61

 disorderly

-0.60

 uninsured

-0.60

 traff

-0.60

BLIC

-0.60

rencies

-0.60

âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ

-0.59

POSITIVE LOGITS

agna

1.19

aign

1.13

agne

1.10

ground

1.01

bell

1.01

camp

0.98

idon

0.91

ing

0.90

sites

0.90

ione

0.90

Activations Density 0.011%

references to a specific location or event named "Camp"

instances of the word "Camp" along with segment delimiters

No Comments

No Known Activations