INDEX

Explanations

causative relationships in sentences

oai_token-act-pair · gpt-3.5-turbo

phrases related to causation

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

urai

-0.75

IFT

-0.66

ullivan

-0.65

oos

-0.65

ography

-0.65

apest

-0.64

fle

-0.63

BILITY

-0.62

atari

-0.62

 Fortune

-0.60

POSITIVE LOGITS

by

1.08

 solely

0.86

 chiefly

0.82

by

0.80

 principally

0.80

BY

0.77

 caused

0.75

 primarily

0.73

 indirectly

0.73

 acutely

0.70

Activations Density 0.092%

causative relationships in sentences

phrases related to causation

No Comments

No Known Activations