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

opoulos

-0.75

 Chandra

-0.74

ebin

-0.73

tis

-0.68

indal

-0.68

ahoo

-0.68

lett

-0.67

arat

-0.67

aeus

-0.67

 Evangel

-0.65

POSITIVE LOGITS

 exits

0.65

 luxury

0.64

FLAG

0.64

liness

0.62

ãĤ¯

0.61

###

0.60

 electronics

0.60

Vert

0.57

 constraints

0.57

foreseen

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.