INDEX

Explanations

questions and inquiries

oai_token-act-pair · gpt-3.5-turbo

questions starting with the word "What."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 favour

-0.76

 reserve

-0.74

 favor

-0.74

 arch

-0.71

 close

-0.67

 receiving

-0.64

 firm

-0.64

 ranking

-0.64

res

-0.63

due

-0.63

POSITIVE LOGITS

What

2.81

Why

2.21

How

2.11

Who

2.08

WHAT

2.05

what

2.04

Where

1.86

Which

1.81

 What

1.77

Whatever

1.70

Activations Density 0.022%

questions and inquiries

questions starting with the word "What."

No Comments

No Known Activations