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

gate

-0.73

nces

-0.70

nels

-0.68

grab

-0.67

icz

-0.67

yip

-0.65

buf

-0.65

nz

-0.65

thumbnails

-0.64

haven

-0.64

POSITIVE LOGITS

 seamless

0.67

onest

0.65

enance

0.65

 word

0.65

 intellig

0.65

å¥³

0.63

 unint

0.62

avering

0.62

Leg

0.61

 Mayer

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.