INDEX

Explanations

references to government entities or organizations with the word "Authority" in their name

oai_token-act-pair · gpt-3.5-turbo

references to various authorities or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

lasses

-0.92

arget

-0.88

 Emin

-0.84

meyer

-0.83

irling

-0.80

ilde

-0.77

boxes

-0.76

lace

-0.76

orget

-0.75

yle

-0.75

POSITIVE LOGITS

 Authority

1.00

uthor

0.78

oun

0.78

BILITY

0.76

stration

0.76

 Board

0.71

alties

0.69

BILITIES

0.67

 administrator

0.67

 delegated

0.66

Activations Density 0.021%

references to government entities or organizations with the word "Authority" in their name

references to various authorities or organizations

No Comments

No Known Activations