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

nor

-0.80

clair

-0.72

sylvania

-0.72

 Rossi

-0.69

berra

-0.68

olia

-0.68

etting

-0.68

warts

-0.67

oda

-0.67

 Dolphin

-0.67

POSITIVE LOGITS

mans

0.76

ributed

0.76

lift

0.74

Charge

0.72

inar

0.72

Correct

0.70

 matt

0.68

GT

0.68

Capt

0.66

cknowled

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.