INDEX

Explanations

predictions or potential future outcomes

oai_token-act-pair · gpt-3.5-turbo

conditional or hypothetical phrases indicating potential outcomes or consequences

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

 copying

-0.70

 Patty

-0.68

 praying

-0.68

 queen

-0.68

 liter

-0.67

 writing

-0.66

 thankful

-0.66

 talking

-0.66

 lucky

-0.65

 touring

-0.63

POSITIVE LOGITS

 preclude

1.12

 diminish

1.08

 motivate

1.07

 outweigh

1.06

 coincide

1.05

 dissu

1.00

 overshadow

0.98

 complicate

0.98

 undermine

0.98

 affect

0.97

Activations Density 0.239%

predictions or potential future outcomes

conditional or hypothetical phrases indicating potential outcomes or consequences

No Comments

No Known Activations