INDEX

Explanations

phrases related to specific topics or arguments discussed in various articles

oai_token-act-pair · gpt-3.5-turbo

the word "that" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 guessing

-0.69

 Riding

-0.62

 Possible

-0.60

ãĥ¬

-0.59

 Oliv

-0.59

 Charg

-0.58

 cuff

-0.58

 Breat

-0.57

Charg

-0.57

Dro

-0.57

POSITIVE LOGITS

 resulted

1.00

 spans

0.96

 culminated

0.96

 accompanies

0.93

 exceeds

0.91

 originated

0.91

 preceded

0.91

 perme

0.90

 arose

0.88

ļéĨĴ

0.87

Activations Density 0.280%

phrases related to specific topics or arguments discussed in various articles

the word "that" in various contexts

No Comments

No Known Activations