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

0:0.07

1:0.07

2:0.08

3:0.07

4:0.09

5:0.07

6:0.09

7:0.08

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

pport

-1.78

itton

-1.57

NetMessage

-1.53

 partName

-1.50

 deferred

-1.48

ourn

-1.47

ummer

-1.42

meric

-1.42

hesda

-1.39

fram

-1.39

POSITIVE LOGITS

��

1.66

rique

1.54

 Trinidad

1.51

 corrid

1.48

 Corona

1.45

 Torres

1.41

 Turtles

1.40

 Yose

1.40

inho

1.39

 Panama

1.38

Activations Density 0.000%

No Known Activations

This feature has no known activations.