INDEX

Explanations

technical terms or acronyms

oai_token-act-pair · gpt-3.5-turbo

proper nouns and specific names related to various topics or categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

assetsadobe

-0.76

ccording

-0.69

©¶æ¥µ

-0.69

 ende

-0.67

 Seym

-0.65

 sqor

-0.62

çĶ°

-0.62

 Heard

-0.60

CLASSIFIED

-0.59

POSITIVE LOGITS

ageddon

0.63

idine

0.63

vered

0.61

eware

0.60

project

0.59

gment

0.59

ind

0.58

containing

0.58

pure

0.57

Fil

0.57

Activations Density 0.290%

technical terms or acronyms

proper nouns and specific names related to various topics or categories

No Comments

No Known Activations