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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ULL

-0.76

ONSORED

-0.71

elling

-0.70

IFA

-0.69

qqa

-0.68

ALD

-0.68

ovember

-0.67

SEA

-0.66

=-=-=-=-

-0.66

ellery

-0.66

POSITIVE LOGITS

canon

0.72

 Volt

0.72

 Vermont

0.63

 Rabb

0.61

 Dial

0.60

 pend

0.60

typ

0.58

 Gott

0.58

Rx

0.56

legal

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.