INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

OPLE

-0.72

tten

-0.67

rolet

-0.66

 Bers

-0.66

ESV

-0.65

 priceless

-0.64

stanbul

-0.64

 Paddock

-0.64

 Palace

-0.62

Bil

-0.61

POSITIVE LOGITS

icons

0.82

Discussion

0.73

label

0.68

seed

0.68

ican

0.68

ized

0.68

 largeDownload

0.67

TBA

0.67

atio

0.67

icus

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.