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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

alin

-0.65

 reins

-0.64

 duty

-0.63

rition

-0.61

iquid

-0.61

 knowledgeable

-0.60

 validity

-0.60

effic

-0.60

 Patient

-0.59

duty

-0.59

POSITIVE LOGITS

pport

0.79

ãĥŃ

0.74

 Bronx

0.72

cko

0.69

 Moonlight

0.69

ãĤĵ

0.69

 carp

0.68

 Janeiro

0.67

isoft

0.66

 Journalists

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.