INDEX

Explanations

phrases related to government agencies and regulations

oai_token-act-pair · gpt-3.5-turbo

references to regulatory agencies, particularly in the context of food and drug safety

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

reads

-0.84

eele

-0.77

flows

-0.74

yang

-0.72

ahime

-0.68

steen

-0.68

skirts

-0.66

gow

-0.66

[+

-0.65

zac

-0.64

POSITIVE LOGITS

 Commission

1.16

 Association

1.12

 Regulatory

1.06

 Regulations

1.02

 Bureau

1.00

 Board

0.98

 Regulation

0.96

 Congress

0.94

 Administration

0.92

 Authority

0.88

Activations Density 0.130%

phrases related to government agencies and regulations

references to regulatory agencies, particularly in the context of food and drug safety

No Comments

No Known Activations