INDEX

Explanations

mentions of names of people or organizations

oai_token-act-pair · gpt-3.5-turbo

proper names, particularly individuals and organizations related to media, politics, and events

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

atform

-0.83

FG

-0.70

quarters

-0.67

leneck

-0.65

etheus

-0.64

 psychiat

-0.64

 incom

-0.63

 skelet

-0.62

£ı

-0.61

yright

-0.60

POSITIVE LOGITS

belt

0.81

rome

0.70

uous

0.69

 Hera

0.69

oga

0.67

utsche

0.67

cheat

0.67

atchewan

0.66

pants

0.65

pta

0.64

Activations Density 0.460%

mentions of names of people or organizations

proper names, particularly individuals and organizations related to media, politics, and events

No Comments

No Known Activations