INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.06

2:0.08

3:0.09

4:0.09

5:0.08

6:0.08

7:0.08

8:0.08

9:0.06

10:0.09

11:0.08

Negative Logits

 Mormons

-1.70

 Weasley

-1.66

fit

-1.62

 sque

-1.62

-+-+

-1.61

 tack

-1.57

 ultrasound

-1.56

 Scient

-1.56

 motions

-1.55

 Kislyak

-1.54

POSITIVE LOGITS

region

1.70

arenthood

1.68

population

1.67

pen

1.66

river

1.64

alach

1.63

Af

1.60

angu

1.60

ゴ

1.59

global

1.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.