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

aleigh

-0.82

natureconservancy

-0.78

amy

-0.76

POST

-0.74

estate

-0.73

 suspic

-0.72

aura

-0.71

SELECT

-0.71

Wik

-0.71

vertisement

-0.71

POSITIVE LOGITS

Hue

0.72

ologne

0.71

 Worldwide

0.71

oslov

0.71

Lod

0.70

 Confederacy

0.68

 Heaven

0.68

 Messiah

0.67

hern

0.67

 Purg

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.