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

fruit

-0.81

+(

-0.68

wich

-0.67

fortune

-0.64

avour

-0.62

 Seed

-0.62

 Holo

-0.61

 Hood

-0.60

avorite

-0.59

 Dish

-0.59

POSITIVE LOGITS

atories

0.68

 inspections

0.68

ntil

0.67

 inspectors

0.66

iott

0.64

©¶æ

0.62

 Judd

0.61

naissance

0.61

bats

0.61

 antioxid

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.