INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

1:0.09

2:0.08

3:0.09

4:0.08

5:0.07

6:0.09

7:0.09

8:0.07

9:0.07

10:0.06

11:0.08

Negative Logits

ulence

-1.96

icka

-1.74

film

-1.73

leck

-1.70

ovie

-1.68

orne

-1.67

raint

-1.64

audio

-1.64

WAR

-1.62

ulent

-1.61

POSITIVE LOGITS

���

2.33

��

1.76

xit

1.61

 Drivers

1.58

��

1.55

 Guilty

1.54

 Discrimination

1.51

 Latvia

1.49

=~

1.48

ュ

1.46

Activations Density 0.000%

No Known Activations

This feature has no known activations.