INDEX

Explanations

phrases referring to solutions to problems or challenges

oai_token-act-pair · gpt-3.5-turbo

statements or arguments that assert what something is or is not

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

throp

-0.90

eor

-0.86

iates

-0.70

 largeDownload

-0.67

dit

-0.66

 bothers

-0.64

 stump

-0.64

 violates

-0.62

 senses

-0.62

 pains

-0.60

POSITIVE LOGITS

olation

0.94

 ALWAYS

0.92

not

0.86

 always

0.85

NOT

0.83

 definitely

0.82

 undoubtedly

0.82

 indeed

0.80

 gonna

0.80

 still

0.80

Activations Density 0.195%

phrases referring to solutions to problems or challenges

statements or arguments that assert what something is or is not

No Comments

No Known Activations