INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Abstract

-0.69

ãĥĨãĤ£

-0.68

clear

-0.65

steen

-0.64

 Hello

-0.64

itude

-0.63

 Samson

-0.63

hur

-0.62

AIR

-0.61

tell

-0.60

POSITIVE LOGITS

 ranc

0.75

ndra

0.74

redo

0.72

ĪĴ

0.71

 vine

0.67

 Longh

0.67

 taxp

0.67

yip

0.65

 cryptoc

0.63

pus

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.