INDEX

Explanations

references to things being planned or prepared in advance

oai_token-act-pair · gpt-3.5-turbo

words that start with the prefix "pre-"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

loo

-0.94

ãĥīãĥ©ãĤ´ãĥ³

-0.84

adesh

-0.71

 GOODMAN

-0.71

owship

-0.69

DEV

-0.66

ãĤ¼ãĤ¦ãĤ¹

-0.66

IBLE

-0.64

boat

-0.64

oice

-0.63

POSITIVE LOGITS

cision

1.15

hend

1.07

requisites

1.02

fecture

1.00

hens

0.99

fect

0.97

pared

0.97

requisite

0.95

empt

0.90

cedented

0.89

Activations Density 0.014%

references to things being planned or prepared in advance

words that start with the prefix "pre-"

No Comments

No Known Activations