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

ãĤ¼ãĤ¦ãĤ¹

-0.71

inventoryQuantity

-0.70

REDACTED

-0.66

 famine

-0.65

Frag

-0.65

rawdownloadcloneembedreportprint

-0.64

WithNo

-0.64

Else

-0.63

Ð´

-0.62

 orig

-0.61

POSITIVE LOGITS

ackle

0.76

ĪĴ

0.72

inding

0.71

alist

0.70

 Advocate

0.69

atory

0.69

©¶æ

0.68

arak

0.68

rosc

0.68

roud

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.