INDEX

Explanations

phrases related to making decisions or choices

oai_token-act-pair · gpt-3.5-turbo

references to competition or selection processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

unctions

-0.73

venants

-0.72

ossibility

-0.65

unction

-0.65

quartered

-0.64

llah

-0.63

ouble

-0.63

enegger

-0.62

urry

-0.62

taboola

-0.61

POSITIVE LOGITS

liest

0.87

 versus

0.81

?",

0.79

?,

0.77

vs

0.72

 depends

0.69

FN

0.68

 hardest

0.68

Accessory

0.67

 weakest

0.65

Activations Density 0.271%

phrases related to making decisions or choices

references to competition or selection processes

No Comments

No Known Activations