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

amber

-0.65

 Prophet

-0.63

 infer

-0.62

DragonMagazine

-0.62

)]

-0.62

Py

-0.61

osate

-0.60

 bour

-0.60

 aven

-0.60

 vengeance

-0.59

POSITIVE LOGITS

ILS

0.88

ICAN

0.84

PRESS

0.77

lic

0.77

ãĥĩãĤ£

0.76

BILITIES

0.75

TE

0.73

ESS

0.72

HI

0.71

JECT

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.