INDEX

Explanations

proper nouns referring to specific entities, such as names of people or locations

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the."

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

thood

-0.75

 namely

-0.69

 depended

-0.68

 derives

-0.67

 relates

-0.67

lessness

-0.66

manship

-0.63

 relies

-0.62

atonin

-0.62

uid

-0.62

POSITIVE LOGITS

 entirety

1.20

 entire

1.16

 halls

1.16

 countryside

1.15

 same

1.12

 streets

1.08

 confines

1.07

 globe

1.05

 skies

1.00

 realm

0.96

Activations Density 0.375%

proper nouns referring to specific entities, such as names of people or locations

occurrences of the word "the."

No Comments

No Known Activations