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

ortex

-0.70

èª

-0.69

jriwal

-0.69

åī

-0.69

alys

-0.69

è¦

-0.68

ocalypse

-0.67

ä»£

-0.66

èĪ

-0.66

mobi

-0.65

POSITIVE LOGITS

atar

0.75

 Mond

0.73

 Jimmy

0.72

eter

0.72

omet

0.70

 Malt

0.67

Ms

0.66

 Mons

0.66

ials

0.63

 Virgin

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.