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

emia

-0.70

arta

-0.65

 Mushroom

-0.64

IU

-0.64

abet

-0.63

rha

-0.62

 Hipp

-0.62

ocus

-0.61

 Peach

-0.60

 heartbeat

-0.60

POSITIVE LOGITS

drops

0.83

yip

0.74

packs

0.74

BUG

0.69

icides

0.68

handler

0.65

ignt

0.65

 intervene

0.64

NG

0.64

thens

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.