INDEX

Explanations

words related to statistical methods of analyzing cause-and-effect relationships

oai_token-act-pair · gpt-3.5-turbo

phrases related to cause-and-effect analysis

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

oak

-0.81

hov

-0.78

pher

-0.75

nesday

-0.72

pired

-0.70

pires

-0.68

kered

-0.67

unts

-0.67

natureconservancy

-0.67

 Mahjong

-0.66

POSITIVE LOGITS

 cure

0.86

 remission

0.84

reatment

0.76

 efficacy

0.71

 termination

0.71

 characterization

0.70

 antidepress

0.69

answer

0.67

 deletion

0.67

effect

0.65

Activations Density 0.275%

words related to statistical methods of analyzing cause-and-effect relationships

phrases related to cause-and-effect analysis

No Comments

No Known Activations