INDEX

Explanations

movie ratings (M) or movie-related information

oai_token-act-pair · gpt-3.5-turbo

mentions of the letter "M" 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 @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 foul

-0.67

 pony

-0.66

 blot

-0.66

 hottest

-0.65

 debunked

-0.65

 Mellon

-0.64

 Eleven

-0.64

 Strip

-0.64

Uri

-0.64

 Mane

-0.63

POSITIVE LOGITS

ountain

1.29

useum

1.26

umbai

1.23

arijuana

1.22

ISSION

1.22

igrant

1.21

unicip

1.21

igration

1.21

ikhail

1.20

ovies

1.20

Activations Density 0.042%

movie ratings (M) or movie-related information

mentions of the letter "M" in various contexts

No Comments

No Known Activations