INDEX

Explanations

terminology related to policies and regulations

oai_token-act-pair · gpt-3.5-turbo

references to regulations and guidelines within official statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 blockers

-0.63

odon

-0.60

 redu

-0.59

ãĤĮ

-0.56

Jr

-0.56

hedon

-0.54

 ILCS

-0.52

 transitions

-0.52

qv

-0.52

 increments

-0.52

POSITIVE LOGITS

 unanimously

0.64

reditation

0.64

its

0.62

 investigating

0.60

 recommending

0.59

Its

0.59

 accredited

0.57

ĸļ

0.57

 publishing

0.57

Plugin

0.56

Activations Density 0.841%

terminology related to policies and regulations

references to regulations and guidelines within official statements

No Comments

No Known Activations