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

 flavors

-0.71

rals

-0.71

ssl

-0.70

pees

-0.68

azon

-0.68

nw

-0.67

cknow

-0.66

gettable

-0.66

 overflow

-0.66

cul

-0.66

POSITIVE LOGITS

ARDS

0.72

ARK

0.71

iment

0.69

 Sutherland

0.67

 Robbie

0.67

amon

0.65

 Maur

0.64

Mor

0.62

 Manager

0.60

ents

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.