INDEX

Explanations

verbs related to causes or effects

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate causation or outcomes

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

anooga

-0.90

 fortun

-0.68

jon

-0.61

quickShipAvailable

-0.61

oret

-0.59

 Compass

-0.58

 Kara

-0.57

FX

-0.57

resy

-0.56

 Telegram

-0.56

POSITIVE LOGITS

 stumble

1.05

 pursue

1.02

 contemplate

0.95

 ponder

0.93

 indulge

0.92

 rethink

0.91

 engage

0.90

 realize

0.90

 retire

0.90

othy

0.90

Activations Density 0.105%

verbs related to causes or effects

phrases that indicate causation or outcomes

No Comments

No Known Activations