INDEX

Explanations

proper names

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Th"

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

ãģ®éŃĶ

-0.83

keeping

-0.81

-0.78

tops

-0.74

Tokens

-0.74

ITED

-0.74

assetsadobe

-0.73

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.71

EMENT

-0.70

 Canaver

-0.68

POSITIVE LOGITS

ought

1.15

reshold

1.13

irteen

1.13

irst

1.10

ailand

1.03

ieving

1.03

ttp

1.03

ieves

1.01

ousand

1.01

aum

1.00

Activations Density 0.020%

proper names

occurrences of the word "Th"

No Comments

No Known Activations