INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

soDeliveryDate

-0.73

patch

-0.72

 triangles

-0.71

behind

-0.71

packed

-0.69

headers

-0.67

 targ

-0.65

ears

-0.65

achine

-0.64

ibia

-0.64

POSITIVE LOGITS

,,,,,,,,

0.75

 Mane

0.69

ÂłÂłÂłÂłÂłÂłÂłÂł

0.69

âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦

0.69

 ______

0.66

%%

0.63

 Morales

0.63

Aut

0.62

Hof

0.60

Â¶

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.