INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

glas

-0.92

iltration

-0.86

pta

-0.74

regate

-0.73

mission

-0.71

izont

-0.70

stream

-0.68

mega

-0.67

lace

-0.67

leys

-0.67

POSITIVE LOGITS

 expires

0.61

âĹ¼

0.60

 subscribed

0.59

NetMessage

0.59

 ticking

0.59

ÂłÂłÂł

0.59

 survived

0.58

 harvested

0.58

 expired

0.57

ocrat

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.