INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

liest

-0.91

 Deity

-0.86

lihood

-0.71

nah

-0.71

Topics

-0.70

nu

-0.70

cha

-0.67

yden

-0.66

vre

-0.65

 Pearce

-0.65

POSITIVE LOGITS

vernment

0.69

 compute

0.67

 boxed

0.67

axis

0.67

ãĤ¬

0.66

 wired

0.66

 Shotgun

0.63

ooters

0.63

 backwards

0.62

ocular

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.