INDEX

Explanations

sponsorship-related terms or phrases

oai_token-act-pair · gpt-3.5-turbo

references to sponsors or sponsorship

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Shant

-0.84

 pend

-0.75

 Warfare

-0.69

Pav

-0.68

 Holmes

-0.67

selves

-0.65

 Detective

-0.63

otom

-0.63

Tud

-0.63

ering

-0.62

POSITIVE LOGITS

 sponsor

1.24

 sponsors

1.15

 sponsorship

1.07

 sponsoring

1.05

 sponsored

1.00

 Spons

0.96

hips

0.93

Spons

0.92

orship

0.90

sponsored

0.82

Activations Density 0.010%

sponsorship-related terms or phrases

references to sponsors or sponsorship

No Comments

No Known Activations