INDEX

Explanations

mentions of the name "Nick"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Nick."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Glob

-0.74

Qur

-0.69

 kinderg

-0.65

 Ministry

-0.65

 ministries

-0.63

âĹ¼

-0.62

QUEST

-0.59

 Jehovah

-0.59

GF

-0.59

 miscar

-0.59

POSITIVE LOGITS

ety

1.20

named

1.18

laus

1.11

ellen

0.89

hattan

0.86

knife

0.83

nect

0.83

haw

0.83

nick

0.82

emonic

0.81

Activations Density 0.009%

mentions of the name "Nick"

occurrences of the name "Nick."

No Comments

No Known Activations