INDEX

Explanations

phrases or names containing the word "de"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the token "de."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

allery

-0.86

 tremend

-0.75

iggins

-0.71

 occas

-0.68

abilia

-0.66

sit

-0.66

okin

-0.65

oun

-0.64

hetti

-0.64

ĸļ

-0.64

POSITIVE LOGITS

utsche

1.26

ploy

1.25

legate

1.20

leted

1.13

legates

1.11

cember

1.09

hyde

1.07

bris

1.06

cker

0.99

VICE

0.91

Activations Density 0.015%

phrases or names containing the word "de"

occurrences of the token "de."

No Comments

No Known Activations