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

shed

-0.74

Wiki

-0.69

 Unlock

-0.66

 Fram

-0.66

tu

-0.64

 Activision

-0.64

 Okawaru

-0.62

 inherit

-0.61

pod

-0.61

reon

-0.61

POSITIVE LOGITS

eg

0.71

 predec

0.65

 crop

0.65

versive

0.64

äº

0.64

elight

0.63

 trickle

0.63

aturdays

0.62

ccording

0.61

arp

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.