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

hur

-0.69

 guiActiveUnfocused

-0.68

Adds

-0.67

atan

-0.65

chard

-0.65

 Adds

-0.64

 largeDownload

-0.62

 guiName

-0.61

 Reprodu

-0.61

 Expand

-0.60

POSITIVE LOGITS

tions

0.74

 interrogated

0.69

 ancest

0.68

 cort

0.67

 adolesc

0.66

idine

0.66

Dos

0.65

 reperto

0.65

ãĤ¦ãĤ¹

0.64

 hemor

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.