INDEX

Explanations

mentions of people or characters named "Madding" or variations of it

oai_token-act-pair · gpt-3.5-turbo

instances of the word "add" or phrases related to addition

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

ãĥīãĥ©ãĤ´ãĥ³

-0.77

tem

-0.66

NING

-0.65

è¦ļéĨĴ

-0.63

âĸ¬

-0.63

 Consumer

-0.62

bane

-0.62

Consumer

-0.61

Â·Â·

-0.61

 Maker

-0.60

POSITIVE LOGITS

icted

1.34

iction

1.20

itionally

1.18

itional

1.18

icts

1.16

resses

1.09

ition

1.08

ressed

1.06

ictive

1.05

ity

1.02

Activations Density 0.008%

mentions of people or characters named "Madding" or variations of it

instances of the word "add" or phrases related to addition

No Comments

No Known Activations