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

0:0.07

1:0.08

2:0.07

3:0.07

4:0.09

5:0.08

6:0.09

7:0.07

8:0.09

9:0.08

10:0.07

11:0.08

Negative Logits

Ug

-1.67

 Tome

-1.67

Tig

-1.56

 Torrent

-1.53

 Typhoon

-1.49

 Nanto

-1.44

Rae

-1.43

 Thrones

-1.37

 Spears

-1.36

-1.32

POSITIVE LOGITS

icultural

1.68

uminum

1.66

posure

1.59

ertodd

1.58

ysis

1.57

omsky

1.53

roma

1.50

uces

1.47

cock

1.47

iculture

1.45

Activations Density 0.000%

No Known Activations

This feature has no known activations.