INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

illard

-0.69

Untitled

-0.67

ESE

-0.67

'';

-0.63

pard

-0.62

bender

-0.62

odiac

-0.62

 Kelly

-0.62

inic

-0.61

wright

-0.61

POSITIVE LOGITS

BuyableInstoreAndOnline

0.75

CPI

0.70

rar

0.68

hots

0.64

 lessons

0.64

 Thumbnails

0.62

 lesson

0.62

itably

0.62

href

0.61

 Spoiler

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.