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

asca

-0.91

 skelet

-0.81

MpServer

-0.80

cko

-0.75

asus

-0.72

 submar

-0.70

 Anders

-0.69

pher

-0.67

 slic

-0.67

cised

-0.67

POSITIVE LOGITS

 Monitor

0.69

KY

0.68

ENTION

0.67

]=

0.65

EMA

0.65

ELF

0.65

ihar

0.64

Track

0.64

Label

0.63

exit

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.