INDEX

Explanations

names occurring at the end of sentences preceded by 'n'

oai_token-act-pair · gpt-3.5-turbo

the letter 'n' 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 @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 incent

-0.66

xual

-0.64

 laun

-0.63

 caution

-0.62

 DRAG

-0.62

 compe

-0.61

 welf

-0.59

 Proced

-0.59

 unsupported

-0.58

 Wasteland

-0.58

POSITIVE LOGITS

orthern

1.19

uggets

1.17

ihil

1.13

aturally

1.11

ovation

1.10

ipeg

1.07

aughty

1.05

umerous

1.05

acht

1.05

ounced

1.04

Activations Density 0.050%

names occurring at the end of sentences preceded by 'n'

the letter 'n' in various contexts

No Comments

No Known Activations