INDEX

Explanations

phrases related to a specific name "Ho."

oai_token-act-pair · gpt-3.5-turbo

the name "Ho" or variations of it within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

Interstitial

-0.75

affer

-0.73

urgical

-0.71

SQL

-0.70

 certs

-0.69

 tabl

-0.69

rpm

-0.69

acus

-0.68

 delim

-0.66

ropolitan

-0.65

POSITIVE LOGITS

Ho

3.70

Ho

2.77

ho

1.80

ho

1.76

HO

1.72

Hoo

1.43

Lo

1.28

Hop

1.25

Wo

1.18

Hof

1.17

Activations Density 0.016%

phrases related to a specific name "Ho."

the name "Ho" or variations of it within the text

No Comments

No Known Activations