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

âĶĢâĶĢ

-0.77

ãĥ

-0.73

âĶ

-0.71

 largeDownload

-0.68

ãĥŁ

-0.67

ãĤ½

-0.66

 CLSID

-0.64

Ó

-0.64

irgin

-0.64

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

-0.64

POSITIVE LOGITS

grain

0.78

enta

0.74

{"

0.66

rency

0.66

CHAT

0.66

pill

0.64

cil

0.63

yne

0.63

alde

0.61

="/

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.