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

agging

-0.75

 Explosion

-0.73

 Electric

-0.67

imeter

-0.67

 Dinosaur

-0.66

 System

-0.65

Cooldown

-0.65

MRI

-0.62

 Generator

-0.60

Mob

-0.59

POSITIVE LOGITS

caps

0.81

 stewards

0.74

wcs

0.74

ensis

0.73

etsk

0.72

 partName

0.67

cki

0.66

prus

0.66

 snowball

0.65

 archae

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.