INDEX

Explanations

an inquiry or prompt for user engagement

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.09

1:0.07

2:0.09

3:0.07

4:0.08

5:0.06

6:0.09

7:0.08

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

 extrater

-3.09

 bending

-2.91

 seismic

-2.78

 sonic

-2.67

 intrusive

-2.61

 lunar

-2.55

 eaves

-2.55

 powering

-2.52

 writ

-2.51

 Lunar

-2.47

POSITIVE LOGITS

avg

2.97

TD

2.73

 Kamp

2.69

 Malk

2.63

 Stam

2.58

chuk

2.56

 Bust

2.54

Medic

2.54

CHAT

2.52

avia

2.52

Activations Density 0.000%

an inquiry or prompt for user engagement

No Known Activations