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

warts

-0.80

etooth

-0.77

afort

-0.74

pport

-0.74

ĵĺ

-0.70

²¾

-0.69

ĺħ

-0.69

 Dwarf

-0.68

ħĭ

-0.68

geons

-0.66

POSITIVE LOGITS

TX

0.76

arag

0.68

DEA

0.67

 Hyde

0.67

fuck

0.64

 deductible

0.63

wagen

0.63

aquin

0.63

RX

0.63

Rx

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.