INDEX

Explanations

the word "collection" and related terms

oai_token-act-pair · gpt-3.5-turbo

phrases that reference various collections of items or works

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

pher

-0.81

yl

-0.68

abad

-0.67

FER

-0.62

forth

-0.61

expected

-0.60

 unden

-0.60

mic

-0.60

ffe

-0.58

generic

-0.57

POSITIVE LOGITS

collection

0.94

 collection

0.88

 Collection

0.84

uably

0.83

 collections

0.80

icles

0.80

naire

0.78

 Collections

0.77

ĸļ

0.74

ieu

0.72

Activations Density 0.034%

the word "collection" and related terms

phrases that reference various collections of items or works

No Comments

No Known Activations