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

ãĤ¦ãĤ¹

-0.76

atcher

-0.76

 Lancet

-0.66

rodu

-0.65

éĥ

-0.64

ancock

-0.64

 Merchants

-0.64

 Mulcair

-0.62

yrim

-0.62

correct

-0.62

POSITIVE LOGITS

 sidx

0.74

 bids

0.67

pport

0.67

 eccentric

0.67

asc

0.65

haz

0.63

neys

0.63

isol

0.62

 aggress

0.61

cam

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.