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

lio

-0.78

 lecturer

-0.74

 misunder

-0.69

iferation

-0.67

ifer

-0.66

 polled

-0.65

avement

-0.65

 marqu

-0.63

 quar

-0.63

 lecture

-0.62

POSITIVE LOGITS

thumbnails

0.82

merce

0.80

doms

0.76

 WATCHED

0.69

EStreamFrame

0.68

/#

0.68

 Reps

0.67

reads

0.67

tackle

0.66

tsy

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.