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

1:0.08

2:0.07

3:0.07

4:0.08

5:0.08

6:0.07

7:0.08

8:0.08

9:0.10

10:0.08

11:0.08

Negative Logits

QC

-1.62

Interstitial

-1.61

raviolet

-1.50

 sprint

-1.47

 rapport

-1.46

 amplification

-1.45

 verbal

-1.43

 amplify

-1.42

eele

-1.40

 endurance

-1.39

POSITIVE LOGITS

selage

1.75

andal

1.68

ajor

1.68

 Sakuya

1.63

ーティ

1.60

osate

1.60

atra

1.58

afia

1.55

agar

1.55

furt

1.53

Activations Density 0.000%

No Known Activations

This feature has no known activations.