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

ida

-0.73

ggle

-0.72

ronics

-0.68

task

-0.67

trial

-0.67

ongo

-0.67

aban

-0.67

 Balloon

-0.67

Daily

-0.64

OND

-0.64

POSITIVE LOGITS

natureconservancy

0.75

 orphans

0.70

 displacement

0.68

ãĤ´ãĥ³

0.62

estamp

0.62

ãĤ¦ãĤ¹

0.62

ocated

0.62

 pools

0.61

 cripp

0.59

arov

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.