INDEX

Explanations

phrases related to plans or intentions

oai_token-act-pair · gpt-3.5-turbo

variations of the word "inspire" and related forms

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

 Pand

-0.66

Kle

-0.64

 Surv

-0.64

 independence

-0.64

Luck

-0.64

Obj

-0.61

 unic

-0.61

kn

-0.60

amon

-0.60

Pew

-0.60

POSITIVE LOGITS

pired

1.42

pire

1.25

pires

1.07

interstitial

1.02

piring

0.99

 confir

0.96

ĸļ

0.92

umbnail

0.89

upiter

0.88

 conspiring

0.86

Activations Density 0.024%

phrases related to plans or intentions

variations of the word "inspire" and related forms

No Comments

No Known Activations