INDEX

Explanations

words related to a specific individual named "Mos."

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

istics

-0.83

istically

-0.76

istical

-0.68

istic

-0.65

 Immunity

-0.65

OWS

-0.65

ocument

-0.64

 Volks

-0.64

UX

-0.64

OWN

-0.63

POSITIVE LOGITS

quit

1.18

aic

1.13

daq

1.10

qu

1.03

cow

1.02

henko

1.01

ques

1.00

chal

0.99

sey

0.98

hin

0.97

Activations Density 0.043%

words related to a specific individual named "Mos."

No Comments

No Known Activations