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

7:0.09

8:0.07

9:0.08

10:0.07

11:0.08

Negative Logits

uten

-1.67

TP

-1.64

ы

-1.64

 Hath

-1.61

 regulars

-1.58

 Ages

-1.58

 Reeves

-1.55

 Assassins

-1.54

 ultras

-1.51

Bey

-1.49

POSITIVE LOGITS

gradient

1.60

pection

1.58

itive

1.57

ommod

1.51

netflix

1.47

acerb

1.47

itarian

1.46

mand

1.46

itivity

1.46

(-

1.45

Activations Density 0.000%

No Known Activations

This feature has no known activations.