INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

igm

-0.78

otom

-0.71

 barg

-0.67

gas

-0.67

ongh

-0.65

afe

-0.65

 motions

-0.62

aly

-0.62

tsky

-0.61

bda

-0.60

POSITIVE LOGITS

mouth

0.83

 hatched

0.70

>]

0.67

ilogy

0.65

è£ħ

0.64

DragonMagazine

0.62

 teasp

0.61

uckland

0.61

 Reach

0.60

 unlocked

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.