INDEX

Explanations

phrases related to news articles or headlines

oai_token-act-pair · gpt-3.5-turbo

instances of significant numerical data or identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

tro

-0.85

 overtime

-0.81

 taxi

-0.75

wet

-0.74

 increment

-0.74

 applicable

-0.74

 subsequent

-0.74

 bailout

-0.73

 confir

-0.72

 agre

-0.72

POSITIVE LOGITS

Offline

1.63

Joined

1.52

Legendary

1.51

Premium

1.46

Member

1.46

Posts

1.44

Born

1.41

Age

1.36

Dear

1.36

Executive

1.36

Activations Density 0.218%

phrases related to news articles or headlines

instances of significant numerical data or identifiers

No Comments

No Known Activations