INDEX

Explanations

references to specific amounts of money

oai_token-act-pair · gpt-3.5-turbo

references to monetary amounts in pounds

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 Ital

-0.73

 Tall

-0.72

ographed

-0.70

ifest

-0.70

 Zucker

-0.66

atives

-0.64

lication

-0.64

umbn

-0.63

Lub

-0.61

 appar

-0.61

POSITIVE LOGITS

Â£

1.45

©¶æ¥µ

1.01

 Â£

1.00

USD

0.94

0.86

 (Â£

0.86

/$

0.85

$$

0.84

âĤ¬

0.83

urious

0.80

Activations Density 0.012%

references to specific amounts of money

references to monetary amounts in pounds

No Comments

No Known Activations