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

catentry

-0.80

 Thrones

-0.70

rencies

-0.68

 highs

-0.64

quickShipAvailable

-0.64

 Houth

-0.63

 praise

-0.63

 Values

-0.63

 GOODMAN

-0.63

POSITIVE LOGITS

veland

0.74

existing

0.70

iard

0.70

oak

0.69

assed

0.67

Queen

0.66

wine

0.66

neck

0.66

iner

0.65

iners

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.