INDEX

Explanations

phrases indicating high level of preparation or uniqueness

oai_token-act-pair · gpt-3.5-turbo

words that begin 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ãĥīãĥ©ãĤ´ãĥ³

-0.80

loo

-0.78

è¦ļéĨĴ

-0.74

oice

-0.72

 Weir

-0.67

IBLE

-0.66

 GOODMAN

-0.66

BuyableInstoreAndOnline

-0.65

THING

-0.63

ãĤ¼ãĤ¦ãĤ¹

-0.63

POSITIVE LOGITS

cision

1.19

requisite

1.09

pared

1.09

cise

1.08

requisites

1.08

ference

1.05

hens

1.04

hend

1.03

cious

1.03

fecture

1.01

Activations Density 0.024%

phrases indicating high level of preparation or uniqueness

words that begin with the prefix "pre-"

No Comments

No Known Activations