INDEX

Explanations

phrases related to policies, regulations, and financial transactions

oai_token-act-pair · gpt-3.5-turbo

topics related to social justice and discrimination issues

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

 largeDownload

-0.67

DK

-0.63

_>

-0.63

Dialogue

-0.62

CONCLUS

-0.61

canon

-0.60

APTER

-0.59

ilogy

-0.59

ovie

-0.58

ruary

-0.58

POSITIVE LOGITS

 themselves

0.87

 their

0.78

 illegally

0.71

 theirs

0.71

 harmful

0.70

entimes

0.69

their

0.69

 unwanted

0.68

 lifestyles

0.67

 costly

0.67

Activations Density 2.100%

phrases related to policies, regulations, and financial transactions

topics related to social justice and discrimination issues

No Comments

No Known Activations