INDEX

Explanations

instances of the word "so" used as an intensifier

oai_token-act-pair · gpt-3.5-turbo

the word "so" 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

ropolitan

-0.65

wreck

-0.65

 glances

-0.61

 cradle

-0.58

idity

-0.57

 Dive

-0.57

 acre

-0.57

haven

-0.54

 disbelief

-0.54

 arrival

-0.54

POSITIVE LOGITS

bered

1.13

oths

1.10

oooo

1.03

othes

1.01

othe

1.00

ooo

1.00

apy

0.98

zin

0.97

oooooooo

0.95

oooooooooooooooo

0.93

Activations Density 0.093%

instances of the word "so" used as an intensifier

the word "so" in various contexts

No Comments

No Known Activations