INDEX

Explanations

words related to visual media or technology

oai_token-act-pair · gpt-3.5-turbo

words starting with the letter "l."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥ¼ãĥĨãĤ£

-0.76

éĹĺ

-0.74

ãĥ¯ãĥ³

-0.71

ãĤ®

-0.69

OLOGY

-0.68

lished

-0.68

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.64

ãĥ¼ãĤ¯

-0.64

chell

-0.63

hower

-0.62

POSITIVE LOGITS

adders

1.32

ibrarian

1.24

ibr

1.23

idd

1.17

ugs

1.16

ips

1.15

ashes

1.15

ipp

1.14

onel

1.13

ongh

1.13

Activations Density 0.024%

words related to visual media or technology

words starting with the letter "l."

No Comments

No Known Activations