INDEX

Explanations

tutorial-related phrases and instructions

oai_token-act-pair · gpt-3.5-turbo

instructional content about tutorials and guides

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ylum

-0.90

olitics

-0.73

ears

-0.72

mouth

-0.71

qqa

-0.71

ocaust

-0.71

 Rasmussen

-0.70

Naz

-0.70

heimer

-0.69

 UNCLASSIFIED

-0.69

POSITIVE LOGITS

how

1.48

HOW

1.25

 basics

1.21

 installing

1.16

how

1.14

How

1.13

How

1.11

 optimizing

1.11

 Config

1.08

why

1.08

Activations Density 0.318%

tutorial-related phrases and instructions

instructional content about tutorials and guides

No Comments

No Known Activations