INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

AW

-0.67

heny

-0.65

emb

-0.64

de

-0.64

EB

-0.63

bys

-0.62

gui

-0.62

 clutch

-0.61

fry

-0.60

TON

-0.59

POSITIVE LOGITS

ngth

0.73

 Palest

0.71

ashtra

0.71

irth

0.70

Untitled

0.69

aimon

0.68

ceiver

0.68

mble

0.68

ologue

0.68

 Coat

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.