INDEX

Explanations

terms or acronyms used in various contexts, including derogatory terms, abbreviations, and scientific jargon

oai_token-act-pair · gpt-3.5-turbo

language related to terminology and classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

thumbnails

-0.68

ramid

-0.67

imeo

-0.62

 incremental

-0.62

oppable

-0.62

phis

-0.61

Vaj

-0.61

oulos

-0.61

erker

-0.60

duino

-0.59

POSITIVE LOGITS

 coined

1.19

ciation

1.02

 referring

0.96

 shorthand

0.95

 meaning

0.95

 synonymous

0.93

ename

0.88

 describing

0.85

 Meaning

0.85

names

0.85

Activations Density 0.105%

terms or acronyms used in various contexts, including derogatory terms, abbreviations, and scientific jargon

language related to terminology and classifications

No Comments

No Known Activations