INDEX

Explanations

keywords related to locations or places within a sentence

oai_token-act-pair · gpt-3.5-turbo

the definite article "the."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tons

-0.77

artifacts

-0.72

pee

-0.71

laden

-0.63

 incorrectly

-0.61

ussia

-0.61

forces

-0.59

lift

-0.59

kens

-0.58

ãĤĵ

-0.57

POSITIVE LOGITS

 outset

1.27

 moment

1.23

 same

1.23

end

1.08

 behest

1.03

 forefront

0.99

 time

0.98

 beginning

0.98

 height

0.95

 heart

0.93

Activations Density 0.049%

keywords related to locations or places within a sentence

the definite article "the."

No Comments

No Known Activations