INDEX

Explanations

references to specific locations or entities denoted by the letter "M"

oai_token-act-pair · gpt-3.5-turbo

references to the letter 'M'

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

 Extras

-0.72

ãĤ¡

-0.69

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.68

 Pose

-0.67

 Beyond

-0.64

 yours

-0.64

 begg

-0.62

 vacant

-0.62

 solicitation

-0.62

 tips

-0.62

POSITIVE LOGITS

ugg

1.21

apping

1.17

OST

1.16

astern

1.16

oto

1.14

aim

1.14

ONEY

1.12

akin

1.11

ains

1.11

ael

1.11

Activations Density 0.034%

references to specific locations or entities denoted by the letter "M"

references to the letter 'M'

No Comments

No Known Activations