INDEX

Explanations

words related to technology and devices, particularly with a focus on "te" in the activation values

oai_token-act-pair · gpt-3.5-turbo

the presence of the word "te" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 timelines

-0.66

 eleph

-0.65

espie

-0.64

 margins

-0.63

 caps

-0.63

 fronts

-0.62

 FISA

-0.62

 flaw

-0.62

 SHALL

-0.62

 containment

-0.59

POSITIVE LOGITS

brate

1.30

brates

1.21

ppo

1.19

te

1.16

achers

1.15

eca

1.12

levision

1.10

llers

1.07

ller

1.05

acher

0.99

Activations Density 0.012%

words related to technology and devices, particularly with a focus on "te" in the activation values

the presence of the word "te" in various contexts

No Comments

No Known Activations