INDEX

Explanations

references to the Indian space agency, "Chandrayaan"

oai_token-act-pair · gpt-3.5-turbo

mentions of specific names or entities, particularly variations of the name "Chand"

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

istered

-0.79

andise

-0.79

isons

-0.72

 Territories

-0.71

DIT

-0.70

ADE

-0.69

cean

-0.67

Tube

-0.66

umenthal

-0.66

ISTER

-0.66

POSITIVE LOGITS

enhagen

0.97

»Ĵ

0.95

rab

0.92

nis

0.90

borgh

0.90

ership

0.87

enberg

0.78

nam

0.77

erey

0.75

lies

0.74

Activations Density 0.036%

references to the Indian space agency, "Chandrayaan"

mentions of specific names or entities, particularly variations of the name "Chand"

No Comments

No Known Activations