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

-0.75

?),

-0.70

obe

-0.70

?).

-0.69

????

-0.69

ague

-0.68

ULT

-0.68

$$$$

-0.68

thus

-0.66

POSITIVE LOGITS

 showc

0.78

Magikarp

0.67

 mosqu

0.67

akuya

0.66

ufact

0.60

isine

0.60

laus

0.59

 Corm

0.59

 Dragons

0.58

 Celest

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.