INDEX

Explanations

references to objects or devices that are "built" with specific features or attributes

oai_token-act-pair · gpt-3.5-turbo

references to items or features that are 'built in'

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Cruel

-0.72

 Unsure

-0.72

 Shooter

-0.70

ican

-0.67

andra

-0.66

uel

-0.65

apple

-0.64

Published

-0.63

FFFF

-0.62

 Shooting

-0.61

POSITIVE LOGITS

built

0.84

 constructed

0.82

packs

0.79

urally

0.73

 bridges

0.72

 decks

0.71

ILD

0.70

 atop

0.69

raper

0.66

aepernick

0.66

Activations Density 0.035%

references to objects or devices that are "built" with specific features or attributes

references to items or features that are 'built in'

No Comments

No Known Activations