INDEX

Explanations

mentions of individuals and their actions, especially on social media platforms

oai_token-act-pair · gpt-3.5-turbo

references to social media influencers and their content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

aucus

-0.72

malink

-0.69

reement

-0.68

OULD

-0.67

 Manufacturer

-0.65

oyer

-0.65

enario

-0.65

reset

-0.63

 Agreement

-0.63

umbledore

-0.63

POSITIVE LOGITS

 himself

1.03

 advoc

1.01

 tours

0.99

 videos

0.98

 stunts

0.97

 seminars

0.97

 exhibitions

0.96

 speeches

0.96

 lectures

0.96

his

0.94

Activations Density 0.860%

mentions of individuals and their actions, especially on social media platforms

references to social media influencers and their content

No Comments

No Known Activations