INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nee

-0.70

nesia

-0.70

onite

-0.68

uts

-0.67

inas

-0.66

folio

-0.66

ramid

-0.64

 femin

-0.63

 conceal

-0.63

 è£ıè

-0.62

POSITIVE LOGITS

ulkan

0.70

raged

0.65

 Merry

0.64

bridge

0.61

 Rolls

0.60

 CARD

0.60

 Rage

0.60

recent

0.60

 McMaster

0.59

pared

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.