INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Intent

-0.72

 guiActiveUn

-0.71

 Crunch

-0.70

£ı

-0.68

ãĥĥ

-0.68

ĸļ

-0.65

ãĥ£

-0.64

 synchronized

-0.63

 coloring

-0.62

ãĥ¼ãĥĨãĤ£

-0.62

POSITIVE LOGITS

lde

0.79

oil

0.74

uld

0.71

Ã»

0.70

arf

0.70

ynt

0.68

UB

0.67

 aber

0.66

bye

0.66

hap

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.