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

inoa

-0.85

ortunate

-0.77

ected

-0.67

paralleled

-0.66

olve

-0.66

idge

-0.65

chell

-0.64

abbit

-0.63

terday

-0.62

anamo

-0.62

POSITIVE LOGITS

£ı

0.80

HOU

0.70

aceae

0.69

sbm

0.69

spir

0.68

Ń

0.67

house

0.66

)]

0.65

 kisses

0.64

GIF

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.