INDEX

Explanations

Keywords related to specific events, topics, or entities mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

topics related to events, institutions, and organizations

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

 Entered

-0.70

ensical

-0.67

DUP

-0.62

 helicop

-0.62

bestos

-0.61

quickShipAvailable

-0.60

Lv

-0.59

 Hogan

-0.59

 Hait

-0.57

 antidepressants

-0.57

POSITIVE LOGITS

 itself

0.82

reciation

0.69

lists

0.66

assadors

0.66

owners

0.62

 themselves

0.60

wiki

0.59

lite

0.59

clusion

0.59

XT

0.58

Activations Density 0.829%

Keywords related to specific events, topics, or entities mentioned in the text

topics related to events, institutions, and organizations

No Comments

No Known Activations