INDEX

Explanations

economic and financial terms or concepts

oai_token-act-pair · gpt-3.5-turbo

references to policies and provisions related to social support and financial regulation

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

wow

-0.85

fuck

-0.74

aclysm

-0.73

iddle

-0.72

 stumble

-0.72

 Wrath

-0.72

wreck

-0.70

ogie

-0.68

agonist

-0.68

================================

-0.67

POSITIVE LOGITS

 prohibitions

1.26

 compulsory

1.17

 mandatory

1.15

 banning

1.15

 prohibiting

1.14

 requiring

1.13

 bans

1.10

 quotas

1.06

 restrictions

1.05

 stricter

1.05

Activations Density 0.411%

economic and financial terms or concepts

references to policies and provisions related to social support and financial regulation

No Comments

No Known Activations