INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Racer

-0.70

 Bundy

-0.69

Ń·

-0.68

Ire

-0.68

ãĤ¹ãĥĪ

-0.66

mr

-0.64

 Reserved

-0.64

bos

-0.64

é¾

-0.63

ãĤ´ãĥ³

-0.62

POSITIVE LOGITS

iation

0.67

upp

0.67

conn

0.67

 genders

0.65

defense

0.65

ories

0.62

igsaw

0.62

hes

0.62

fits

0.61

gradation

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.