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

\\\\\\\\

-0.83

è¦ļéĨĴ

-0.75

 GOODMAN

-0.75

EMOTE

-0.72

ä»

-0.70

Interested

-0.68

 firsthand

-0.67

Mount

-0.65

ãģĮ

-0.65

EV

-0.64

POSITIVE LOGITS

heit

0.82

£ı

0.64

jury

0.63

lycer

0.63

issue

0.61

ulkan

0.60

pard

0.60

 kinetic

0.60

furt

0.60

mus

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.