INDEX

Explanations

references to a specific location or character named "Pop"

oai_token-act-pair · gpt-3.5-turbo

references to "Pop" culture or related entities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

OME

-0.80

IGHTS

-0.76

RAW

-0.71

%%%%

-0.70

IVES

-0.68

Reloaded

-0.68

beit

-0.66

BILITIES

-0.66

åŃĲ

-0.66

 Corm

-0.63

POSITIVE LOGITS

corn

1.28

ulations

1.28

ulating

1.23

ulates

1.21

ulated

1.20

ularity

1.19

ular

1.12

ulate

1.07

ulation

1.05

ulators

0.98

Activations Density 0.021%

references to a specific location or character named "Pop"

references to "Pop" culture or related entities

No Comments

No Known Activations