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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uckland

-0.99

otton

-0.74

ishable

-0.72

è¦ļéĨĴ

-0.70

ushima

-0.68

animous

-0.67

arsity

-0.67

uggle

-0.66

ãĤĵ

-0.66

ttp

-0.66

POSITIVE LOGITS

 like

1.12

 LIKE

0.87

geist

0.81

 likes

0.81

 akin

0.80

 liking

0.79

 Like

0.77

 boom

0.74

 liked

0.72

 unlike

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.