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

©¶æ¥µ

-0.74

 Uriel

-0.66

--------------------------------------------------------

-0.66

prototype

-0.66

ynt

-0.65

Ĥİ

-0.65

²¾

-0.62

 Pyth

-0.62

 casualty

-0.60

Geh

-0.60

POSITIVE LOGITS

ļéĨĴ

0.74

 pend

0.69

 dolphin

0.67

edin

0.66

 bait

0.66

uyomi

0.65

0.64

opus

0.62

 colored

0.61

ozo

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.