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

ahime

-0.93

olitan

-0.71

 retribution

-0.70

 Warfare

-0.68

 Pict

-0.67

allery

-0.66

 Clash

-0.64

abwe

-0.64

 Trooper

-0.63

naire

-0.63

POSITIVE LOGITS

GE

0.71

glass

0.70

angel

0.69

restrial

0.67

 pasture

0.65

LAND

0.65

bugs

0.63

HOME

0.63

lands

0.62

Land

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.