INDEX

Explanations

phrases indicating a high level of impact or importance

oai_token-act-pair · gpt-3.5-turbo

terms indicating magnitude or severity of issues

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

ilk

-0.77

ifice

-0.74

apple

-0.70

ramid

-0.68

claimer

-0.67

obile

-0.65

naire

-0.65

ften

-0.65

washer

-0.65

 Puzzle

-0.64

POSITIVE LOGITS

 amounts

1.39

 quantities

1.11

 doses

1.02

 levels

0.94

 proportions

0.93

 indications

0.90

 sums

0.88

 enough

0.86

 lows

0.86

 parallels

0.84

Activations Density 0.281%

phrases indicating a high level of impact or importance

terms indicating magnitude or severity of issues

No Comments

No Known Activations

phrases indicating a high level of impact or importance

terms indicating magnitude or severity of issues

No Comments

No Known Activations