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

ollen

-0.79

etts

-0.73

lish

-0.72

usercontent

-0.72

Upload

-0.72

dule

-0.71

arta

-0.70

scl

-0.69

soDeliveryDate

-0.68

arte

-0.67

POSITIVE LOGITS

 Bullets

0.74

 Ferry

0.68

quiet

0.62

hog

0.61

izations

0.61

Ori

0.61

©¶æ

0.59

Iw

0.59

 Sunny

0.58

 Fukushima

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.