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

etsk

-0.74

udden

-0.72

 CARE

-0.71

ansom

-0.69

unte

-0.68

heast

-0.67

osure

-0.66

 econom

-0.65

rehend

-0.65

aiman

-0.64

POSITIVE LOGITS

ãĥĥãĤ¯

0.78

shire

0.77

sed

0.70

 riding

0.69

 cruising

0.69

uld

0.69

 squid

0.68

ãĤ´ãĥ³

0.67

 horsepower

0.65

 chrome

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.