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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Deus

-0.67

sis

-0.66

tery

-0.65

nce

-0.65

 destroyer

-0.64

 cutter

-0.63

eur

-0.61

ndra

-0.61

 Walters

-0.60

hoe

-0.59

POSITIVE LOGITS

sonian

0.78

ĺħ

0.74

IQ

0.72

Afee

0.72

onen

0.71

FUL

0.71

veland

0.68

Ali

0.68

PHOTOS

0.68

animous

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.