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

 Gors

-0.70

 Indigenous

-0.66

 Cosponsors

-0.65

Byr

-0.62

 Burgess

-0.61

 Pryor

-0.61

 Beir

-0.60

ificantly

-0.59

 Awakens

-0.57

 Aboriginal

-0.56

POSITIVE LOGITS

natureconservancy

0.75

kef

0.74

âĢ¦]

0.72

ahead

0.72

catentry

0.71

uxe

0.69

nu

0.68

ernel

0.66

resso

0.66

.}

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.