INDEX

Explanations

complex words or terms containing "aph", with a higher preference for those with "aph" followed by the number 9

oai_token-act-pair · gpt-3.5-turbo

instances of the substring "aph" within text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

PUT

-0.76

nings

-0.75

âĸ¬âĸ¬

-0.74

swick

-0.66

 Alps

-0.64

PDATE

-0.63

LOAD

-0.62

ced

-0.61

 fitting

-0.61

 Schwarzenegger

-0.61

POSITIVE LOGITS

obia

1.21

ysics

1.21

ysical

1.16

obic

1.09

orically

1.07

osate

1.04

orns

1.00

orical

0.98

urst

0.97

oria

0.96

Activations Density 0.026%

complex words or terms containing "aph", with a higher preference for those with "aph" followed by the number 9

instances of the substring "aph" within text

No Comments

No Known Activations