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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

geoning

-0.85

bler

-0.78

pee

-0.73

mys

-0.71

tan

-0.71

eway

-0.70

pin

-0.68

ller

-0.67

crow

-0.67

arr

-0.67

POSITIVE LOGITS

 ILCS

0.71

-+-+

0.71

IDES

0.69

 Definitions

0.68

STATE

0.67

 Dominion

0.67

TIT

0.67

 Pref

0.66

OULD

0.63

 Skydragon

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.