INDEX

Explanations

terms related to email newsletters

oai_token-act-pair · gpt-3.5-turbo

phrases related to news delivery and updates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

yo

-0.78

 theoret

-0.67

ivas

-0.67

urally

-0.66

fitting

-0.66

asio

-0.65

Kik

-0.65

urat

-0.64

igree

-0.63

adm

-0.63

POSITIVE LOGITS

Content

0.81

content

0.79

article

0.74

Brow

0.74

 headlines

0.73

 satire

0.73

 alerts

0.71

 content

0.71

 Updates

0.69

Interstitial

0.69

Activations Density 0.073%

terms related to email newsletters

phrases related to news delivery and updates

No Comments

No Known Activations