INDEX

Explanations

instances of the word "one."

oai_token-act-pair · gpt-3.5-turbo

the word "one," indicating a focus on singularity or individual perspectives 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 @ 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

tnc

-0.93

united

-0.70

tein

-0.70

ahime

-0.69

urations

-0.68

soDeliveryDate

-0.67

YN

-0.64

utenberg

-0.63

 Presence

-0.63

ult

-0.62

POSITIVE LOGITS

 else

1.72

 cares

1.18

 bothered

1.14

 knows

1.12

 Else

1.11

Else

1.11

else

1.11

 cared

1.04

 bothers

1.02

 expects

0.99

Activations Density 0.056%

instances of the word "one."

the word "one," indicating a focus on singularity or individual perspectives in various contexts

No Comments

No Known Activations