INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

podcast

-0.70

 dynamically

-0.67

Single

-0.66

stories

-0.66

DOS

-0.65

éŃĶ

-0.65

UV

-0.65

Tier

-0.63

 ourselves

-0.62

VK

-0.61

POSITIVE LOGITS

agements

0.86

strate

0.81

ument

0.71

inence

0.71

gaard

0.68

velt

0.68

ossip

0.67

 Dent

0.66

ceptive

0.66

 divest

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.