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

 respons

-0.80

 taxed

-0.71

 indu

-0.68

slave

-0.66

 presses

-0.65

forces

-0.65

iasco

-0.64

 harassed

-0.64

 symp

-0.64

 persecuted

-0.63

POSITIVE LOGITS

 Built

0.70

Writing

0.69

âĢ²

0.67

 Writing

0.66

 Spaces

0.65

Ago

0.65

 Achievements

0.64

alling

0.63

 Fast

0.63

Ã¥

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.