INDEX

Explanations

the word "Iz" and various inflections of it

oai_token-act-pair · gpt-3.5-turbo

the presence of the name "Khan" and related characters

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

quartered

-0.92

¥ŀ

-0.71

srf

-0.67

riott

-0.67

 whistle

-0.67

 hitch

-0.66

etheless

-0.65

 respawn

-0.64

 horns

-0.63

 flock

-0.63

POSITIVE LOGITS

arro

1.31

ombie

1.12

uku

0.95

hou

0.93

hao

0.92

enegger

0.91

umi

0.90

awa

0.87

oids

0.86

abal

0.86

Activations Density 0.017%

the word "Iz" and various inflections of it

the presence of the name "Khan" and related characters

No Comments

No Known Activations