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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IVER

-0.67

annah

-0.66

IUM

-0.65

 pane

-0.64

oven

-0.62

MN

-0.61

isSpecialOrderable

-0.61

plates

-0.61

iamond

-0.61

 redes

-0.60

POSITIVE LOGITS

Woo

0.71

enberg

0.66

 Donn

0.65

 Doyle

0.65

 widow

0.64

 Addiction

0.64

 Disapp

0.62

 Aging

0.61

 antibodies

0.60

Downloadha

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.