INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.3.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

0:0.09

1:0.07

2:0.08

3:0.09

4:0.09

5:0.07

6:0.07

7:0.08

8:0.07

9:0.07

10:0.09

11:0.07

Negative Logits

…]

-1.57

['

-1.36

 manifestations

-1.35

fed

-1.32

"""

-1.32

Ms

-1.29

fed

-1.29

 Senators

-1.27

wat

-1.25

 studied

-1.24

POSITIVE LOGITS

 teasp

1.70

�

1.60

maximum

1.59

glomer

1.59

terness

1.55

 accur

1.55

enium

1.47

cipline

1.46

ept

1.45

ズ

1.44

Activations Density 0.000%

No Known Activations

This feature has no known activations.