INDEX

Explanations

No Explanations Found

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

Not in Any Lists

No Comments

Head Attr Weights

0:0.09

1:0.07

2:0.07

3:0.10

4:0.08

5:0.08

6:0.08

7:0.07

8:0.10

9:0.08

10:0.07

11:0.07

Negative Logits

Buc

-2.99

 Giles

-2.84

 Kell

-2.83

ayne

-2.75

 Apprentice

-2.74

 sacked

-2.69

ALD

-2.67

Bac

-2.63

 Sands

-2.62

byss

-2.61

POSITIVE LOGITS

}}}

2.79

 diffusion

2.73

qv

2.61

 microscopic

2.54

 intermedi

2.46

 spectators

2.46

 superflu

2.42

ット

2.41

 relay

2.40

 Lieberman

2.40

Activations Density 0.000%

No Known Activations

This feature has no known activations.