INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

area

-0.74

Berry

-0.70

 poppy

-0.69

undown

-0.67

brance

-0.62

Union

-0.61

 Berm

-0.61

 Browne

-0.61

 Tablet

-0.60

Isa

-0.58

POSITIVE LOGITS

 Mistress

0.75

soDeliveryDate

0.73

esi

0.72

 Emin

0.72

sed

0.71

esses

0.69

atars

0.67

maid

0.66

lik

0.65

Pred

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.