INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ires

-0.74

ļéĨĴ

-0.74

ukong

-0.66

 stool

-0.66

 Deliver

-0.65

 Trailer

-0.65

 alike

-0.63

hetto

-0.62

 typew

-0.62

 reel

-0.62

POSITIVE LOGITS

orders

0.79

urrent

0.76

rary

0.72

order

0.71

aults

0.69

agame

0.68

ported

0.68

azo

0.67

ordered

0.66

batch

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.