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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

sole

-0.86

quickShipAvailable

-0.81

 skelet

-0.74

 withd

-0.71

panic

-0.68

 guts

-0.67

orst

-0.65

=\"

-0.64

ãĤ©

-0.64

BALL

-0.63

POSITIVE LOGITS

 enjoy

0.69

 Detected

0.67

 Enjoy

0.65

pine

0.63

 Nile

0.62

hander

0.62

 Wonders

0.62

properties

0.62

lling

0.61

pecting

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.