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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.05

2:0.08

3:0.09

4:0.08

5:0.06

6:0.09

7:0.08

8:0.08

9:0.07

10:0.10

11:0.07

Negative Logits

MpServer

-2.01

undo

-1.95

iking

-1.86

��

-1.84

lying

-1.81

ulating

-1.71

trl

-1.64

pair

-1.64

�

-1.63

igslist

-1.63

POSITIVE LOGITS

 memoir

1.52

 atmosp

1.51

!'"

1.51

 AUTH

1.50

 martyr

1.49

 cath

1.49

abal

1.48

 ster

1.47

 Kafka

1.47

JECT

1.46

Activations Density 0.000%

No Known Activations

This feature has no known activations.