INDEX

Explanations

quantitative changes or comparisons in various situations

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate changes or variations measured in percentages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

hid

-0.72

finished

-0.71

 succeeds

-0.69

itialized

-0.68

argon

-0.66

istar

-0.66

wine

-0.65

 succeeded

-0.65

rology

-0.63

agate

-0.63

POSITIVE LOGITS

 leaps

1.10

 virtue

0.90

 fractions

0.90

 trillions

0.87

 approximately

0.86

 fiat

0.85

 half

0.84

 nearly

0.84

Activations Density 0.069%

quantitative changes or comparisons in various situations

phrases that indicate changes or variations measured in percentages

No Comments

No Known Activations