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

 Totem

-0.68

ront

-0.67

 Miko

-0.66

 Talks

-0.64

liction

-0.64

uffle

-0.63

 discipline

-0.60

ppa

-0.59

ussions

-0.59

 Diary

-0.59

POSITIVE LOGITS

iaries

0.79

Italy

0.74

ä»

0.74

Bey

0.72

Bro

0.69

Marg

0.68

atra

0.67

senal

0.67

Spain

0.67

æĥ

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.