INDEX

Explanations

personal care product items and medical terms

oai_token-act-pair · gpt-3.5-turbo

specific nouns and terms related to various categories and contexts, such as toiletries, medical terminology, political terms, and legality

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

ernels

-0.72

assies

-0.67

sites

-0.66

 Rooms

-0.63

eworks

-0.62

 Machines

-0.61

rooms

-0.61

 Vaugh

-0.61

events

-0.60

places

-0.57

POSITIVE LOGITS

 standpoint

0.71

 perspective

0.62

 apology

0.61

 spokesperson

0.59

 statement

0.58

 variant

0.55

 diagnosis

0.55

 illustration

0.53

 piece

0.53

 degree

0.53

Activations Density 1.079%

personal care product items and medical terms

specific nouns and terms related to various categories and contexts, such as toiletries, medical terminology, political terms, and legality

No Comments

No Known Activations