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

INGTON

-0.73

 Installation

-0.70

 Babe

-0.67

emi

-0.62

 Pebble

-0.61

 Shack

-0.61

])

-0.61

bert

-0.60

Kw

-0.60

 thereafter

-0.58

POSITIVE LOGITS

cade

0.90

gue

0.67

alogue

0.67

olson

0.67

yne

0.66

hement

0.65

umenthal

0.64

Ń·

0.64

pas

0.62

apps

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.