INDEX

Explanations

phrases related to software tools and features

oai_token-act-pair · gpt-3.5-turbo

references to add-ons in software applications

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

Ķ

-0.76

wind

-0.73

eve

-0.71

WIND

-0.69

Chief

-0.69

chief

-0.67

¦

-0.67

ª

-0.66

ENG

-0.66

Wind

-0.65

POSITIVE LOGITS

 functionality

0.81

ition

0.79

 addon

0.75

 goodies

0.73

izable

0.72

 platforms

0.72

istries

0.72

 subscriptions

0.71

antically

0.71

isations

0.70

Activations Density 0.036%

phrases related to software tools and features

references to add-ons in software applications

No Comments

No Known Activations