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

1:0.08

2:0.07

3:0.08

4:0.08

5:0.08

6:0.07

7:0.09

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

ilee

-1.69

egu

-1.62

ushima

-1.59

ocobo

-1.55

eur

-1.52

 acknow

-1.51

oard

-1.51

 ashore

-1.51

resses

-1.47

catching

-1.47

POSITIVE LOGITS

 Jews

1.60

 Hebrew

1.57

LDS

1.53

 Mormons

1.53

Kab

1.48

 Quran

1.46

 Juda

1.45

 Horus

1.43

 livestream

1.41

 Abrams

1.40

Activations Density 0.000%

No Known Activations

This feature has no known activations.