INDEX

Explanations

words related to regulations, safety measures, and other criteria associated with vehicles and transportation

oai_token-act-pair · gpt-3.5-turbo

terms related to safety regulations and vehicle management

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

tur

-0.77

wolf

-0.62

åĤ

-0.61

achable

-0.59

CRE

-0.59

factor

-0.57

æĦ

-0.56

 Wolves

-0.56

heit

-0.56

iable

-0.56

POSITIVE LOGITS

iasco

0.67

 Cosponsors

0.65

reciation

0.62

 Archdemon

0.62

 Prohibition

0.62

Ã£

0.61

idy

0.60

 Nieto

0.60

 Tycoon

0.60

vertisements

0.60

Activations Density 0.392%

words related to regulations, safety measures, and other criteria associated with vehicles and transportation

terms related to safety regulations and vehicle management

No Comments

No Known Activations