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

 Artemis

-0.65

iod

-0.62

exit

-0.60

TER

-0.60

endif

-0.58

pet

-0.58

conservancy

-0.58

 Remain

-0.56

EL

-0.56

imo

-0.56

POSITIVE LOGITS

swick

0.67

Original

0.67

rawdownloadcloneembedreportprint

0.63

Brow

0.62

 PowerPoint

0.60

ubs

0.60

alth

0.60

zsche

0.60

vern

0.59

ricks

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.