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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 coun

-0.75

HUD

-0.68

ucc

-0.66

acas

-0.66

lance

-0.65

="#

-0.65

[-

-0.63

 congr

-0.62

AFB

-0.61

hattan

-0.61

POSITIVE LOGITS

Ü

0.84

ãĥ¯

0.75

estro

0.71

ãĥ¼ãĥĨãĤ£

0.69

Els

0.68

 possessed

0.67

Origin

0.66

usal

0.62

qt

0.62

anse

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.