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

 seamless

-0.77

Blocks

-0.69

 compat

-0.67

erers

-0.66

 razor

-0.65

 disconnect

-0.64

 Province

-0.64

 porous

-0.63

 Blocks

-0.63

 envis

-0.63

POSITIVE LOGITS

ä½ľ

0.92

0.91

ä»£

0.91

mble

0.84

¬¼

0.83

ĨĴ

0.81

±

0.80

localhost

0.79

ãĤ§

0.78

osate

0.77

Activations Density 0.000%

No Known Activations

This feature has no known activations.