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

Tro

-0.84

 Shooting

-0.72

 Investigation

-0.70

 Trade

-0.69

 Trials

-0.68

boarding

-0.68

 Logic

-0.67

 Seas

-0.67

 Pole

-0.67

Trade

-0.67

POSITIVE LOGITS

enhagen

0.81

 panties

0.75

izabeth

0.74

uko

0.74

urers

0.74

soDeliveryDate

0.73

ppard

0.72

 withd

0.72

aret

0.71

udeb

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.