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

UMP

-0.83

PORT

-0.68

 DeVos

-0.68

paio

-0.67

ummer

-0.63

aunts

-0.61

veland

-0.60

ĪĴ

-0.60

Hub

-0.60

conv

-0.60

POSITIVE LOGITS

 payable

0.75

 Actual

0.75

izoph

0.72

oleon

0.66

ceiver

0.65

ufact

0.62

 ende

0.62

foundland

0.62

 laun

0.61

ategory

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.