INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

0:0.08

1:0.07

2:0.09

3:0.08

4:0.08

5:0.08

6:0.08

7:0.07

8:0.08

9:0.09

10:0.08

11:0.08

Negative Logits

Defense

-1.38

storage

-1.21

rums

-1.17

 Wasteland

-1.17

 Vanderbilt

-1.17

 executives

-1.14

 Ventures

-1.13

 utilities

-1.13

 Precision

-1.12

 Bunker

-1.11

POSITIVE LOGITS

ğ

1.63

iverpool

1.48

awa

1.45

ayn

1.44

aunder

1.42

Í

1.41

omez

1.37

ahime

1.37

ashtra

1.35

 IMAGES

1.34

Activations Density 0.000%

No Known Activations

This feature has no known activations.