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

 tremend

-1.02

rontal

-0.92

 newcom

-0.82

 citiz

-0.81

utherland

-0.79

 arrang

-0.79

estinal

-0.77

 veter

-0.76

 streng

-0.76

 skelet

-0.74

POSITIVE LOGITS

OPS

0.75

 Creative

0.68

ses

0.67

iques

0.67

ãĥ¼ãĤ¯

0.65

++)

0.65

Abu

0.64

 Copyright

0.64

 Writers

0.64

BA

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.