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

ãĤ®

-0.94

ãĥĺ

-0.78

ABE

-0.76

istor

-0.75

ãĤ°

-0.74

omnia

-0.74

 PROG

-0.70

 VIDEOS

-0.69

 è£ıç

-0.69

ESSION

-0.69

POSITIVE LOGITS

 refund

0.73

endi

0.64

 casc

0.63

 disclaim

0.61

 traveller

0.61

 Citizens

0.61

 tribes

0.61

 settlements

0.59

cill

0.59

raged

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.