INDEX

Explanations

people or entities with names starting with the letter 'L' followed by numbers

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter "L" in various contexts

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£

-0.73

 Subtle

-0.73

 Parenthood

-0.67

smanship

-0.67

hower

-0.66

ãĤ¡

-0.64

 Satanic

-0.63

 Prohibition

-0.63

ģĸ

-0.62

 Primal

-0.62

POSITIVE LOGITS

ifestyle

1.23

ibrarian

1.20

adders

1.19

arger

1.19

ayers

1.19

ocker

1.17

umber

1.15

aund

1.15

aptop

1.15

ately

1.13

Activations Density 0.034%

people or entities with names starting with the letter 'L' followed by numbers

occurrences of the letter "L" in various contexts

No Comments

No Known Activations