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

 Trop

-0.69

erg

-0.64

porary

-0.63

Community

-0.61

notes

-0.61

ractions

-0.60

 Clip

-0.60

Lost

-0.59

FN

-0.58

 Refresh

-0.58

POSITIVE LOGITS

imura

0.73

ariat

0.67

 Shutterstock

0.67

 GOODMAN

0.65

atar

0.63

anchester

0.63

ober

0.62

hemy

0.60

hei

0.60

 climates

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.