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

Women

-0.69

ãĥ³ãĤ¸

-0.65

 Thou

-0.64

 Standing

-0.61

ï¿½ï¿½

-0.60

 Guys

-0.60

 comprom

-0.58

 Rost

-0.57

 Women

-0.57

urdue

-0.55

POSITIVE LOGITS

lde

0.88

llan

0.77

sonian

0.76

hall

0.71

browser

0.71

hari

0.70

ilic

0.70

node

0.70

cade

0.69

 Lumpur

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.