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

 arsen

-0.67

uez

-0.65

 cape

-0.65

 descend

-0.64

ItemImage

-0.64

 preval

-0.63

 salute

-0.63

 Sahara

-0.62

 crocod

-0.61

 intent

-0.61

POSITIVE LOGITS

erity

0.95

orie

0.86

Ĥª

0.77

anan

0.76

wered

0.76

erker

0.75

orum

0.72

struction

0.72

emaker

0.71

ueller

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.