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

auld

-0.78

 stakes

-0.75

utical

-0.74

assadors

-0.73

ilibrium

-0.72

oreal

-0.72

inational

-0.67

iosyncr

-0.67

 invested

-0.67

tarians

-0.67

POSITIVE LOGITS

ouston

0.84

 guiActiveUnfocused

0.74

istor

0.70

icago

0.66

arte

0.65

=/

0.65

 Gilbert

0.64

Cell

0.63

 âĨĳ

0.63

\/\/

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.