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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ĸļ

-0.90

↵Âł

-0.74

=-=-

-0.70

pill

-0.68

NetMessage

-0.68

ÂłÂłÂłÂł

-0.67

issues

-0.66

beat

-0.65

aneers

-0.65

album

-0.64

POSITIVE LOGITS

ocracy

0.74

ocratic

0.70

oda

0.70

riz

0.68

isSpecialOrderable

0.67

 Tale

0.65

 deadliest

0.64

ctic

0.63

daq

0.63

heast

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.