INDEX

Explanations

phrases that emphasize a point or convey strong opinions

oai_token-act-pair · gpt-3.5-turbo

instances of the word "that" 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 @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

arson

-0.80

emis

-0.74

ATURES

-0.74

atur

-0.73

IVERS

-0.71

ciples

-0.71

asures

-0.70

ãĥ©ãĥ³

-0.68

urch

-0.66

avers

-0.66

POSITIVE LOGITS

guy

0.94

 translates

0.92

 shouldn

0.92

 kind

0.91

ain

0.90

 sounds

0.88

 doesn

0.88

 reminds

0.88

 proves

0.88

 happens

0.87

Activations Density 0.131%

phrases that emphasize a point or convey strong opinions

instances of the word "that" in various contexts

No Comments

No Known Activations