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

0:0.06

1:0.07

2:0.09

3:0.07

4:0.10

5:0.08

6:0.08

7:0.10

8:0.07

9:0.06

10:0.08

11:0.09

Negative Logits

etheless

-2.17

unknown

-1.81

maximum

-1.60

 fluct

-1.59

 glaring

-1.51

 nonetheless

-1.50

 lowly

-1.49

 awaiting

-1.46

 malfunction

-1.46

Others

-1.45

POSITIVE LOGITS

win

1.68

 Simulator

1.64

 Armory

1.59

DVD

1.58

 Brigade

1.56

 Bread

1.52

 dissertation

1.50

TA

1.48

DVD

1.46

 Symphony

1.46

Activations Density 0.000%

No Known Activations

This feature has no known activations.