INDEX

Explanations

mentions of specific locations, events, and people

oai_token-act-pair · gpt-3.5-turbo

specific entities and key updates in various news reports and happenings

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

 generations

-0.80

 centuries

-0.77

 decades

-0.74

 ÂŃ

-0.73

ielding

-0.70

utterstock

-0.68

 Mehran

-0.67

 society

-0.67

opian

-0.66

 millennia

-0.65

POSITIVE LOGITS

 Yesterday

1.01

 tonight

0.93

 UPDATE

0.91

MIA

0.90

Yesterday

0.89

 congr

0.86

terday

0.84

 Recap

0.84

 recap

0.81

 Updates

0.80

Activations Density 1.288%

mentions of specific locations, events, and people

specific entities and key updates in various news reports and happenings

No Comments

No Known Activations