INDEX

Explanations

proper nouns related to persons or places

oai_token-act-pair · gpt-3.5-turbo

mentions of specific names related to people and organizations

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

atcher

-0.74

 Sparrow

-0.69

ronics

-0.67

asper

-0.63

inating

-0.63

urtles

-0.63

roach

-0.62

ardless

-0.62

 Polo

-0.61

lectic

-0.61

POSITIVE LOGITS

worldly

1.00

nces

0.81

INGTON

0.78

\\\\\\\\

0.78

REDACTED

0.75

 unden

0.73

CLASSIFIED

0.70

imensional

0.70

awa

0.69

DragonMagazine

0.67

Activations Density 0.059%

proper nouns related to persons or places

mentions of specific names related to people and organizations

No Comments

No Known Activations